SlideShare a Scribd company logo
1 of 40
Perception and Intelligence Laboratory
Seoul
National
University
Sketch-based 3D Shape Retrievals
using Convolutional Neural Networks
Fang Wang, Le Kang, Yi Li
Junho Cho
15/11/06
• Sketch-based 3D Shape Retrieval using Convolutional Neural Networks
• CVPR 2015 oral
• Retrieving 3D models from 2D sketches
• http://users.cecs.anu.edu.au/~yili/
• Demo & code: http://users.cecs.anu.edu.au/~yili/cnnsbsr/
Perception and Intelligence Lab., Copyright © 2015 2
Introduction
• Sketch-based is easy input, yet rich enough to specify shapes.
• Early attempts: keywords, 3D shapes as queries
• Directly matching 2D sketches to 3D model is difficult
• Very different representations..
• Many methods 3D models projected to multiple 2D views.
• Then match sketch to one of its views.
• Variations in both sketch styles and 3D models  Low performance
Perception and Intelligence Lab., Copyright © 2015 3
Introduction and Early attempts
• Finding “Best views” for 3D model
• Ideally, one of viewpoint similar to query sketch
• Similarity score using Gabor, dense SIFT and GAILIF
• No guarantee of best views have similar viewpoints with sketches.
• Finding “Best view” is unsolved problem.
• Elusive definition
Perception and Intelligence Lab., Copyright © 2015 4
Early attempts
1. Propose to learn feature representations for sketch based shape
retrieval, bypass dilemma of “Best view” selection.
• Minimalism approach as opposed to multiple best views.
• Just chose 2 views randomly in 3D model with hypothesis.
• Still outperforms, showing features learned efficiently.
2. Two Siamese CNN to learn similarities in both
within-domain and cross domain.
• Sketches and views have distinctive intrinsic property.
• Two different CNN models for sketch and model view.
• Couples two input sources into the same target space.
3. Outperforms
Perception and Intelligence Lab., Copyright © 2015 5
Contributions
Siamese CNN
• CNN
• CNN effectively learn complicated mappings
from raw images to the target.
• Less domain knowledge.
(V.S. handcrafted features and shallow
learning frameworks.)
• Siamese Network
• Two identical sub-convolutional networks.
• Input as pairs of sample
• Similar input pairs  similar output vectors
• Dissimilar input pairs  dissimilar output vectors
• Used in a weakly supervised metric learning setting.
• Applied to text classification, speech feature
classification, Face verification.
Perception and Intelligence Lab., Copyright © 2015 7
CNN & Siamese Network
Perception and Intelligence Lab., Copyright © 2015 8
Perception and Intelligence Lab., Copyright © 2015 9
Learning a Similarity Measure Discriminatively Using a Siamese Network
(S. Chopra, R. Hadsell, and Y. Lecun, CVPR2005)
• Takes two samples, into separate but identical networks.
• Typical loss function defined over pairs.
• 𝑠1, 𝑠2 : two samples
• 𝑦 : binary similarity label. Same 0, Different 1
• 𝐷 𝑤 =∥ 𝑓 𝑠1; 𝑤1 − 𝑓 𝑠2; 𝑤2 ∥1 : distance
• Set 𝛼 =
1
𝐶 𝑝
, 𝛽 = 𝐶 𝑛, 𝛾 = −
2.77
𝐶 𝑛
, where 𝐶p = 0.2, Cn = 10
• Constants from Learning a Similarity Measure Discriminatively Using a Siamese Network
• Input pairs labeled as similar  Bring output vectors closer.
• Input pairs labeled as dissimilar  Push output vectors away.
• Back-propagated gradients computed individually on two sample sets
• Network updated by the average of two gradients
Perception and Intelligence Lab., Copyright © 2015 10
Basic Siamese CNN
Perception and Intelligence Lab., Copyright © 2015 11
𝑦=0 or 1
𝒚
Learning feature representations
for sketch based 3D shape retrieval
Perception and Intelligence Lab., Copyright © 2015 13
Illustrated example of Cross-domain matching
• Two domains: sketch & 3D models view
• (a) Mixed
• Learn correct mapping using pair similarities in each domain (s-s, v-v)
as well as their cross-domain relations (s-v) jointly.
• (b) Then two point sets correctly aligned in the feature space.
• After cross domain metric learning, matching can be performed in
sketch - sketch, view - view, sketch - view
• Basic Siamese Network used for samples from the same domain. (ex s-s, v-v)
• Cross domain setting, propose to extend it to two Siamese Networks,
one for view domain, one for sketch domain
• Define within-domain loss & cross domain loss
• Better performance! (compared to Basic Siamese Network)
Perception and Intelligence Lab., Copyright © 2015 14
Siamese Network for cross-domain matching
• Loss function newly defined
Sim of sketches Sim of views cross domain sim
• 𝑠1, 𝑣1: sketch and view in same class
• 𝑠2, 𝑣2: sketch and view in same class
• 𝑦 : Binary similarity label.
• L:
• Actually, do not use category labels in the framework.
• Possible description of desk? hand? face? doesn’t matter
Perception and Intelligence Lab., Copyright © 2015 15
𝐿(𝑠1, 𝑣2, 𝑦)
• Same network design for both networks, but learned separately.
• Unlikely to basic Siamese Network.
Perception and Intelligence Lab., Copyright © 2015 16
• Only two views from 3D models.
• Opposed to multiple views
• 2 was enough
• 1. Most of 3D models were up-right.
2. Two viewpoints randomly generated, angle difference larger than 45.
• Didn’t focus on best view. Comparing views are beyond the scope of paper.
• With chose viewpoint, generate 2D line drawings.
1. Closed boundaries
2. Suggestive Contours
D.Decarlo. Suggestive contours for conveying shape
Perception and Intelligence Lab., Copyright © 2015 17
View definitions and line drawing rendering
Experiments
• PSB / SBSR dataset
• Widely used for 3D shape retrieval system evaluation
• 1814 3D models
• SBSR: 1814 hand drawn sketches collected using Amazon Mechanical Turk
• SHREC’13 & ‘14 dataset
• PSB Sketches in SBSR dataset not enough
• Imbalanced number of sketches for classes
• Can be biased
• 1258 models, each 80 instances.
• SHREC’14 greatly enlarged. 8987 3D models
• Very hard
• Models from various sources and arbitrarily oriented.
Perception and Intelligence Lab., Copyright © 2015 19
Datasets
1. Precision-recall curve
2. mAP
3. Nearest Neighbor(NN) used to measure top 1 retrieval accuracy
4. E-Measure(E):
harmonic mean of the precision and recall for the top 32 retrieval items
5. First/Second tier (FT/ST) and Discounted cumulated gain(DCG)
as defined in the PSB statistics
Perception and Intelligence Lab., Copyright © 2015 20
Evaluation criteria
• Generating pairs for Siamese network
• Reasonable proportion of similar and dissimilar pairs
• Dissimilar pairs 10x more than similar pairs for successful training.
• Randomly select 2 view pairs in the same category,
• 20 view samples from other categories
• Perform random paring for each training epoch.
• Data augmentation for sketch set
• Randomly performed affine transformations on sketch sample
• Generate more variations on sketches
• Two augmentation for each sketch sample.
Perception and Intelligence Lab., Copyright © 2015 21
Experimental Settings
• Siamese CNN based on Theano
• 2.8GHz CPU and GTX 780 GPU
• With preprocessed view features,
retrieval time about 2 ms on SHREC’13 dataset
• Training time proportional to total # of pairs and # of epochs.
• 2.5 h for PSB/SBSR, 6 h for SHREC’13
• No significant performance gain when increasing views. 210
• Increased computational cost, GPU memory.
• Two views are enough.
Perception and Intelligence Lab., Copyright © 2015 22
Computational cost
Results & Conclusion
• Works very well on popular classes (human, face, plane)
• Fine grained categorizations are difficult to distinguish
• Shelf vs Box. only differ small.
• Semantic ambiguity is very hard
• Barn vs House. Differ in functionality.
• Importance of viewpoint is decreased in this approach.
• Plane, high degree of freedom, still retrieval results are excellent.
Perception and Intelligence Lab., Copyright © 2015 24
Results on PSB/SBSR dataset
• PSB/SBSR is very imbalanced dataset.
• 71 classes are not in training set, only in test set.
• Unseen classes can be retrievable?
Ex) Unseen
class
• Even work well on failure case. (ex. flower  potting plant)
• Demonstrates that it learns similarity effectively.
Perception and Intelligence Lab., Copyright © 2015 25
• Visualization of the learned features.
• PCA on the features into 2D
• Green dots: sketches
• Yellow: views.
• Similar shapes are grouped together
automatically.
• Animals, vehicles …
Perception and Intelligence Lab., Copyright © 2015 26
Results on SHREC
Perception and Intelligence Lab., Copyright © 2015 27
Perception and Intelligence Lab., Copyright © 2015 28
Perception and Intelligence Lab., Copyright © 2015 29
Perception and Intelligence Lab., Copyright © 2015 30
• Precision-recall curve
• Outperforms.
• 10% higher when small recall
• Curve decreases much slower  More stable
• 30% higher when recall reaches 1
Perception and Intelligence Lab., Copyright © 2015 31
• Noticeable over-fitting in training.
• Can be even better
• Standard metrics for comparison
• Performs better in every metric
• Also compared with basic Siamese
• Both sketches & views share the
same network
• Variations in two domains are
different! Confirmed
• Using same features(hand-crafted or
learned) for both domains are bad.
Perception and Intelligence Lab., Copyright © 2015 32
• Within-domain retrieval
• Already provided by dataset,
but recheck the method.
• View domain is more
consistent than sketch domain
• Inconsistency in sketch is
the most challenging issue.
• Powerful in learning features
for both within-domain and
cross-domain
Perception and Intelligence Lab., Copyright © 2015 33
• Proposed to learn feature presentations for sketch based 3D shape retrieval
• Instead of computing “best views”, use predefined viewpoints and
adopt two Siamese CNNs, one for views and one for sketches.
• Bypass dilemma of best view selection
• Experiments show the method is superior.
Perception and Intelligence Lab., Copyright © 2015 34
Conclusion
Thank you
Chapter 01.
• 이거 자체가 learning cross domain similarities 로 해결해서 best views를 정
하는 이슈 없앰
• Minimalism approach as opposed to multiple best views.
• 3D model 자체가 다 위로 생김.
• 2개 이상 비교하는것보다 훨신 효과적임을 보임.
• 이건 결국 feature을 제대로 학습했음을 보여줌.
• Semantic level matching
• Comprehensive shape represenations. Rather than combination of shllow
features that only capture low level visual info
Perception and Intelligence Lab., Copyright © 2015 36
• Learn from CNN
• Use Siamese Network.
• Two input ousrces have distinctive intrinsic property  use 2 differenet CNN
models. Sketch and model.
• More power to capture different proporteis in idff domain.
• Loss function to align the results of two CNN models.
• Couples two input cources into the same targe tspace.
• Compare features directly using a simple distance function.
• Outperforms! Precision recall, NN1. retrievals in each domain effective, fast
computation based on filtering.
Perception and Intelligence Lab., Copyright © 2015 37
• Stopping criteria.
• All three of the datasets had been split into training and testing sets, but no
validation set was specified. Therefore, we terminated our algorithm after 50
epochs for PSB/SBSR and 20 for SHREC’13 dataset (or until convergence).
Multiple runs were performed and the mean values were reported.
Perception and Intelligence Lab., Copyright © 2015 38
Experimental Settings
Method dataset Measure 1 Measure 2 Measure 3 Measure 4
Baseline ABC 92 12 34 45
XXX ABC 32 32 54 76
YYY ABC 14 14 12 98
ZZZ ABC 32 23 32 67
Proposed ABC 14 42 41 87
Proposed (w.XX) ABC 32 15 35 67
Perception and Intelligence Lab., Copyright © 2015 39
Table example
Table Title (if you want it to place here)
Perception and Intelligence Lab., Copyright © 2015 40
Figure example
< Updated cells > < CNN architecture >
For highlight

More Related Content

What's hot

Transfer Learning and Fine Tuning for Cross Domain Image Classification with ...
Transfer Learning and Fine Tuning for Cross Domain Image Classification with ...Transfer Learning and Fine Tuning for Cross Domain Image Classification with ...
Transfer Learning and Fine Tuning for Cross Domain Image Classification with ...Sujit Pal
 
Score-Based Generative Modeling through Stochastic Differential Equations
Score-Based Generative Modeling through Stochastic Differential EquationsScore-Based Generative Modeling through Stochastic Differential Equations
Score-Based Generative Modeling through Stochastic Differential EquationsSangwoo Mo
 
Efficient de cvpr_2020_paper
Efficient de cvpr_2020_paperEfficient de cvpr_2020_paper
Efficient de cvpr_2020_papershanullah3
 
Learning loss for active learning
Learning loss for active learningLearning loss for active learning
Learning loss for active learningNAVER Engineering
 
A Neural Grammatical Error Correction built on Better Pre-training and Sequen...
A Neural Grammatical Error Correction built on Better Pre-training and Sequen...A Neural Grammatical Error Correction built on Better Pre-training and Sequen...
A Neural Grammatical Error Correction built on Better Pre-training and Sequen...NAVER Engineering
 
do adversarially robust image net models transfer better
do adversarially robust image net models transfer betterdo adversarially robust image net models transfer better
do adversarially robust image net models transfer betterLEE HOSEONG
 
Saliency-based Models of Image Content and their Application to Auto-Annotati...
Saliency-based Models of Image Content and their Application to Auto-Annotati...Saliency-based Models of Image Content and their Application to Auto-Annotati...
Saliency-based Models of Image Content and their Application to Auto-Annotati...Jonathon Hare
 
MVTec AD: A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection
MVTec AD: A Comprehensive Real-World Dataset for Unsupervised Anomaly DetectionMVTec AD: A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection
MVTec AD: A Comprehensive Real-World Dataset for Unsupervised Anomaly DetectionLEE HOSEONG
 
Salient KeypointSelection for Object Representation
Salient KeypointSelection for Object RepresentationSalient KeypointSelection for Object Representation
Salient KeypointSelection for Object RepresentationPrerana Mukherjee
 
Transfer Learning: An overview
Transfer Learning: An overviewTransfer Learning: An overview
Transfer Learning: An overviewjins0618
 
Deep Learning Made Easy with Deep Features
Deep Learning Made Easy with Deep FeaturesDeep Learning Made Easy with Deep Features
Deep Learning Made Easy with Deep FeaturesTuri, Inc.
 
Building Continuous Learning Systems
Building Continuous Learning SystemsBuilding Continuous Learning Systems
Building Continuous Learning SystemsAnuj Gupta
 
Talk@rmit 09112017
Talk@rmit 09112017Talk@rmit 09112017
Talk@rmit 09112017Shuai Zhang
 
Introduction to machine learning
Introduction to machine learningIntroduction to machine learning
Introduction to machine learningSanghamitra Deb
 
160205 NeuralArt - Understanding Neural Representation
160205 NeuralArt - Understanding Neural Representation160205 NeuralArt - Understanding Neural Representation
160205 NeuralArt - Understanding Neural RepresentationJunho Cho
 
“Modern Machine Vision from Basics to Advanced Deep Learning,” a Presentation...
“Modern Machine Vision from Basics to Advanced Deep Learning,” a Presentation...“Modern Machine Vision from Basics to Advanced Deep Learning,” a Presentation...
“Modern Machine Vision from Basics to Advanced Deep Learning,” a Presentation...Edge AI and Vision Alliance
 
Human uncertainty makes classification more robust, ICCV 2019 Review
Human uncertainty makes classification more robust, ICCV 2019 ReviewHuman uncertainty makes classification more robust, ICCV 2019 Review
Human uncertainty makes classification more robust, ICCV 2019 ReviewLEE HOSEONG
 
Image Translation with GAN
Image Translation with GANImage Translation with GAN
Image Translation with GANJunho Cho
 
Super resolution in deep learning era - Jaejun Yoo
Super resolution in deep learning era - Jaejun YooSuper resolution in deep learning era - Jaejun Yoo
Super resolution in deep learning era - Jaejun YooJaeJun Yoo
 
Scalable image recognition model with deep embedding
Scalable image recognition model with deep embeddingScalable image recognition model with deep embedding
Scalable image recognition model with deep embedding捷恩 蔡
 

What's hot (20)

Transfer Learning and Fine Tuning for Cross Domain Image Classification with ...
Transfer Learning and Fine Tuning for Cross Domain Image Classification with ...Transfer Learning and Fine Tuning for Cross Domain Image Classification with ...
Transfer Learning and Fine Tuning for Cross Domain Image Classification with ...
 
Score-Based Generative Modeling through Stochastic Differential Equations
Score-Based Generative Modeling through Stochastic Differential EquationsScore-Based Generative Modeling through Stochastic Differential Equations
Score-Based Generative Modeling through Stochastic Differential Equations
 
Efficient de cvpr_2020_paper
Efficient de cvpr_2020_paperEfficient de cvpr_2020_paper
Efficient de cvpr_2020_paper
 
Learning loss for active learning
Learning loss for active learningLearning loss for active learning
Learning loss for active learning
 
A Neural Grammatical Error Correction built on Better Pre-training and Sequen...
A Neural Grammatical Error Correction built on Better Pre-training and Sequen...A Neural Grammatical Error Correction built on Better Pre-training and Sequen...
A Neural Grammatical Error Correction built on Better Pre-training and Sequen...
 
do adversarially robust image net models transfer better
do adversarially robust image net models transfer betterdo adversarially robust image net models transfer better
do adversarially robust image net models transfer better
 
Saliency-based Models of Image Content and their Application to Auto-Annotati...
Saliency-based Models of Image Content and their Application to Auto-Annotati...Saliency-based Models of Image Content and their Application to Auto-Annotati...
Saliency-based Models of Image Content and their Application to Auto-Annotati...
 
MVTec AD: A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection
MVTec AD: A Comprehensive Real-World Dataset for Unsupervised Anomaly DetectionMVTec AD: A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection
MVTec AD: A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection
 
Salient KeypointSelection for Object Representation
Salient KeypointSelection for Object RepresentationSalient KeypointSelection for Object Representation
Salient KeypointSelection for Object Representation
 
Transfer Learning: An overview
Transfer Learning: An overviewTransfer Learning: An overview
Transfer Learning: An overview
 
Deep Learning Made Easy with Deep Features
Deep Learning Made Easy with Deep FeaturesDeep Learning Made Easy with Deep Features
Deep Learning Made Easy with Deep Features
 
Building Continuous Learning Systems
Building Continuous Learning SystemsBuilding Continuous Learning Systems
Building Continuous Learning Systems
 
Talk@rmit 09112017
Talk@rmit 09112017Talk@rmit 09112017
Talk@rmit 09112017
 
Introduction to machine learning
Introduction to machine learningIntroduction to machine learning
Introduction to machine learning
 
160205 NeuralArt - Understanding Neural Representation
160205 NeuralArt - Understanding Neural Representation160205 NeuralArt - Understanding Neural Representation
160205 NeuralArt - Understanding Neural Representation
 
“Modern Machine Vision from Basics to Advanced Deep Learning,” a Presentation...
“Modern Machine Vision from Basics to Advanced Deep Learning,” a Presentation...“Modern Machine Vision from Basics to Advanced Deep Learning,” a Presentation...
“Modern Machine Vision from Basics to Advanced Deep Learning,” a Presentation...
 
Human uncertainty makes classification more robust, ICCV 2019 Review
Human uncertainty makes classification more robust, ICCV 2019 ReviewHuman uncertainty makes classification more robust, ICCV 2019 Review
Human uncertainty makes classification more robust, ICCV 2019 Review
 
Image Translation with GAN
Image Translation with GANImage Translation with GAN
Image Translation with GAN
 
Super resolution in deep learning era - Jaejun Yoo
Super resolution in deep learning era - Jaejun YooSuper resolution in deep learning era - Jaejun Yoo
Super resolution in deep learning era - Jaejun Yoo
 
Scalable image recognition model with deep embedding
Scalable image recognition model with deep embeddingScalable image recognition model with deep embedding
Scalable image recognition model with deep embedding
 

Similar to 151106 Sketch-based 3D Shape Retrievals using Convolutional Neural Networks

The Search for a New Visual Search Beyond Language - StampedeCon AI Summit 2017
The Search for a New Visual Search Beyond Language - StampedeCon AI Summit 2017The Search for a New Visual Search Beyond Language - StampedeCon AI Summit 2017
The Search for a New Visual Search Beyond Language - StampedeCon AI Summit 2017StampedeCon
 
ResNeSt: Split-Attention Networks
ResNeSt: Split-Attention NetworksResNeSt: Split-Attention Networks
ResNeSt: Split-Attention NetworksSeunghyun Hwang
 
2019 cvpr paper_overview
2019 cvpr paper_overview2019 cvpr paper_overview
2019 cvpr paper_overviewLEE HOSEONG
 
2019 cvpr paper overview by Ho Seong Lee
2019 cvpr paper overview by Ho Seong Lee2019 cvpr paper overview by Ho Seong Lee
2019 cvpr paper overview by Ho Seong LeeMoazzem Hossain
 
20191107 deeplearningapproachesfornetworks
20191107 deeplearningapproachesfornetworks20191107 deeplearningapproachesfornetworks
20191107 deeplearningapproachesfornetworkstm1966
 
Search to Distill: Pearls are Everywhere but not the Eyes
Search to Distill: Pearls are Everywhere but not the EyesSearch to Distill: Pearls are Everywhere but not the Eyes
Search to Distill: Pearls are Everywhere but not the EyesSungchul Kim
 
Convolutional Neural Networks : Popular Architectures
Convolutional Neural Networks : Popular ArchitecturesConvolutional Neural Networks : Popular Architectures
Convolutional Neural Networks : Popular Architecturesananth
 
李俊良/Feature Engineering in Machine Learning
李俊良/Feature Engineering in Machine Learning李俊良/Feature Engineering in Machine Learning
李俊良/Feature Engineering in Machine Learning台灣資料科學年會
 
"Sparse Graph Attention Networks", IEEE Transactions on Knowledge and Data En...
"Sparse Graph Attention Networks", IEEE Transactions on Knowledge and Data En..."Sparse Graph Attention Networks", IEEE Transactions on Knowledge and Data En...
"Sparse Graph Attention Networks", IEEE Transactions on Knowledge and Data En...ssuser2624f71
 
"Solving Vision Tasks Using Deep Learning: An Introduction," a Presentation f...
"Solving Vision Tasks Using Deep Learning: An Introduction," a Presentation f..."Solving Vision Tasks Using Deep Learning: An Introduction," a Presentation f...
"Solving Vision Tasks Using Deep Learning: An Introduction," a Presentation f...Edge AI and Vision Alliance
 
Image Segmentation Using Deep Learning : A survey
Image Segmentation Using Deep Learning : A surveyImage Segmentation Using Deep Learning : A survey
Image Segmentation Using Deep Learning : A surveyNUPUR YADAV
 
Computer Vision for Beginners
Computer Vision for BeginnersComputer Vision for Beginners
Computer Vision for BeginnersSanghamitra Deb
 
Fcv rep darrell
Fcv rep darrellFcv rep darrell
Fcv rep darrellzukun
 
Moving object detection in complex scene
Moving object detection in complex sceneMoving object detection in complex scene
Moving object detection in complex sceneKumar Mayank
 
CNN vs SIFT-based Visual Localization - Laura Leal-Taixé - UPC Barcelona 2018
CNN vs SIFT-based Visual Localization - Laura Leal-Taixé - UPC Barcelona 2018CNN vs SIFT-based Visual Localization - Laura Leal-Taixé - UPC Barcelona 2018
CNN vs SIFT-based Visual Localization - Laura Leal-Taixé - UPC Barcelona 2018Universitat Politècnica de Catalunya
 
Training Neural Networks
Training Neural NetworksTraining Neural Networks
Training Neural NetworksDatabricks
 
HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...
HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...
HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...Tulipp. Eu
 
Wits presentation 6_28072015
Wits presentation 6_28072015Wits presentation 6_28072015
Wits presentation 6_28072015Beatrice van Eden
 

Similar to 151106 Sketch-based 3D Shape Retrievals using Convolutional Neural Networks (20)

The Search for a New Visual Search Beyond Language - StampedeCon AI Summit 2017
The Search for a New Visual Search Beyond Language - StampedeCon AI Summit 2017The Search for a New Visual Search Beyond Language - StampedeCon AI Summit 2017
The Search for a New Visual Search Beyond Language - StampedeCon AI Summit 2017
 
ResNeSt: Split-Attention Networks
ResNeSt: Split-Attention NetworksResNeSt: Split-Attention Networks
ResNeSt: Split-Attention Networks
 
lec6a.ppt
lec6a.pptlec6a.ppt
lec6a.ppt
 
2019 cvpr paper_overview
2019 cvpr paper_overview2019 cvpr paper_overview
2019 cvpr paper_overview
 
2019 cvpr paper overview by Ho Seong Lee
2019 cvpr paper overview by Ho Seong Lee2019 cvpr paper overview by Ho Seong Lee
2019 cvpr paper overview by Ho Seong Lee
 
20191107 deeplearningapproachesfornetworks
20191107 deeplearningapproachesfornetworks20191107 deeplearningapproachesfornetworks
20191107 deeplearningapproachesfornetworks
 
Search to Distill: Pearls are Everywhere but not the Eyes
Search to Distill: Pearls are Everywhere but not the EyesSearch to Distill: Pearls are Everywhere but not the Eyes
Search to Distill: Pearls are Everywhere but not the Eyes
 
Convolutional Neural Networks : Popular Architectures
Convolutional Neural Networks : Popular ArchitecturesConvolutional Neural Networks : Popular Architectures
Convolutional Neural Networks : Popular Architectures
 
李俊良/Feature Engineering in Machine Learning
李俊良/Feature Engineering in Machine Learning李俊良/Feature Engineering in Machine Learning
李俊良/Feature Engineering in Machine Learning
 
lecture_16_jiajun.pdf
lecture_16_jiajun.pdflecture_16_jiajun.pdf
lecture_16_jiajun.pdf
 
"Sparse Graph Attention Networks", IEEE Transactions on Knowledge and Data En...
"Sparse Graph Attention Networks", IEEE Transactions on Knowledge and Data En..."Sparse Graph Attention Networks", IEEE Transactions on Knowledge and Data En...
"Sparse Graph Attention Networks", IEEE Transactions on Knowledge and Data En...
 
"Solving Vision Tasks Using Deep Learning: An Introduction," a Presentation f...
"Solving Vision Tasks Using Deep Learning: An Introduction," a Presentation f..."Solving Vision Tasks Using Deep Learning: An Introduction," a Presentation f...
"Solving Vision Tasks Using Deep Learning: An Introduction," a Presentation f...
 
Image Segmentation Using Deep Learning : A survey
Image Segmentation Using Deep Learning : A surveyImage Segmentation Using Deep Learning : A survey
Image Segmentation Using Deep Learning : A survey
 
Computer Vision for Beginners
Computer Vision for BeginnersComputer Vision for Beginners
Computer Vision for Beginners
 
Fcv rep darrell
Fcv rep darrellFcv rep darrell
Fcv rep darrell
 
Moving object detection in complex scene
Moving object detection in complex sceneMoving object detection in complex scene
Moving object detection in complex scene
 
CNN vs SIFT-based Visual Localization - Laura Leal-Taixé - UPC Barcelona 2018
CNN vs SIFT-based Visual Localization - Laura Leal-Taixé - UPC Barcelona 2018CNN vs SIFT-based Visual Localization - Laura Leal-Taixé - UPC Barcelona 2018
CNN vs SIFT-based Visual Localization - Laura Leal-Taixé - UPC Barcelona 2018
 
Training Neural Networks
Training Neural NetworksTraining Neural Networks
Training Neural Networks
 
HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...
HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...
HiPEAC 2019 Workshop - Real-Time Modelling Visual Scenes with Biological Insp...
 
Wits presentation 6_28072015
Wits presentation 6_28072015Wits presentation 6_28072015
Wits presentation 6_28072015
 

More from Junho Cho

Get Used to Command Line Interface
Get Used to Command Line InterfaceGet Used to Command Line Interface
Get Used to Command Line InterfaceJunho Cho
 
Convolutional Neural Network
Convolutional Neural NetworkConvolutional Neural Network
Convolutional Neural NetworkJunho Cho
 
160805 End-to-End Memory Networks
160805 End-to-End Memory Networks160805 End-to-End Memory Networks
160805 End-to-End Memory NetworksJunho Cho
 
150807 Fast R-CNN
150807 Fast R-CNN150807 Fast R-CNN
150807 Fast R-CNNJunho Cho
 
150424 Scalable Object Detection using Deep Neural Networks
150424 Scalable Object Detection using Deep Neural Networks150424 Scalable Object Detection using Deep Neural Networks
150424 Scalable Object Detection using Deep Neural NetworksJunho Cho
 
161209 Unsupervised Learning of Video Representations using LSTMs
161209 Unsupervised Learning of Video Representations using LSTMs161209 Unsupervised Learning of Video Representations using LSTMs
161209 Unsupervised Learning of Video Representations using LSTMsJunho Cho
 
Unsupervised Cross-Domain Image Generation
Unsupervised Cross-Domain Image GenerationUnsupervised Cross-Domain Image Generation
Unsupervised Cross-Domain Image GenerationJunho Cho
 

More from Junho Cho (7)

Get Used to Command Line Interface
Get Used to Command Line InterfaceGet Used to Command Line Interface
Get Used to Command Line Interface
 
Convolutional Neural Network
Convolutional Neural NetworkConvolutional Neural Network
Convolutional Neural Network
 
160805 End-to-End Memory Networks
160805 End-to-End Memory Networks160805 End-to-End Memory Networks
160805 End-to-End Memory Networks
 
150807 Fast R-CNN
150807 Fast R-CNN150807 Fast R-CNN
150807 Fast R-CNN
 
150424 Scalable Object Detection using Deep Neural Networks
150424 Scalable Object Detection using Deep Neural Networks150424 Scalable Object Detection using Deep Neural Networks
150424 Scalable Object Detection using Deep Neural Networks
 
161209 Unsupervised Learning of Video Representations using LSTMs
161209 Unsupervised Learning of Video Representations using LSTMs161209 Unsupervised Learning of Video Representations using LSTMs
161209 Unsupervised Learning of Video Representations using LSTMs
 
Unsupervised Cross-Domain Image Generation
Unsupervised Cross-Domain Image GenerationUnsupervised Cross-Domain Image Generation
Unsupervised Cross-Domain Image Generation
 

Recently uploaded

EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM TRACKING WITH GOOGLE ANALYTICS.pptx
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM  TRACKING WITH GOOGLE ANALYTICS.pptxEMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM  TRACKING WITH GOOGLE ANALYTICS.pptx
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM TRACKING WITH GOOGLE ANALYTICS.pptxthyngster
 
Ukraine War presentation: KNOW THE BASICS
Ukraine War presentation: KNOW THE BASICSUkraine War presentation: KNOW THE BASICS
Ukraine War presentation: KNOW THE BASICSAishani27
 
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...Suhani Kapoor
 
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Callshivangimorya083
 
Dubai Call Girls Wifey O52&786472 Call Girls Dubai
Dubai Call Girls Wifey O52&786472 Call Girls DubaiDubai Call Girls Wifey O52&786472 Call Girls Dubai
Dubai Call Girls Wifey O52&786472 Call Girls Dubaihf8803863
 
04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationships04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationshipsccctableauusergroup
 
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Callshivangimorya083
 
VIP High Class Call Girls Bikaner Anushka 8250192130 Independent Escort Servi...
VIP High Class Call Girls Bikaner Anushka 8250192130 Independent Escort Servi...VIP High Class Call Girls Bikaner Anushka 8250192130 Independent Escort Servi...
VIP High Class Call Girls Bikaner Anushka 8250192130 Independent Escort Servi...Suhani Kapoor
 
Invezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signalsInvezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signalsInvezz1
 
High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...
High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...
High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...soniya singh
 
Predicting Employee Churn: A Data-Driven Approach Project Presentation
Predicting Employee Churn: A Data-Driven Approach Project PresentationPredicting Employee Churn: A Data-Driven Approach Project Presentation
Predicting Employee Churn: A Data-Driven Approach Project PresentationBoston Institute of Analytics
 
FESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdfFESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdfMarinCaroMartnezBerg
 
Call Girls In Mahipalpur O9654467111 Escorts Service
Call Girls In Mahipalpur O9654467111  Escorts ServiceCall Girls In Mahipalpur O9654467111  Escorts Service
Call Girls In Mahipalpur O9654467111 Escorts ServiceSapana Sha
 
VIP Call Girls in Amravati Aarohi 8250192130 Independent Escort Service Amravati
VIP Call Girls in Amravati Aarohi 8250192130 Independent Escort Service AmravatiVIP Call Girls in Amravati Aarohi 8250192130 Independent Escort Service Amravati
VIP Call Girls in Amravati Aarohi 8250192130 Independent Escort Service AmravatiSuhani Kapoor
 
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Callshivangimorya083
 
Brighton SEO | April 2024 | Data Storytelling
Brighton SEO | April 2024 | Data StorytellingBrighton SEO | April 2024 | Data Storytelling
Brighton SEO | April 2024 | Data StorytellingNeil Barnes
 
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...dajasot375
 
100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptxAnupama Kate
 
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.pptdokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.pptSonatrach
 

Recently uploaded (20)

EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM TRACKING WITH GOOGLE ANALYTICS.pptx
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM  TRACKING WITH GOOGLE ANALYTICS.pptxEMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM  TRACKING WITH GOOGLE ANALYTICS.pptx
EMERCE - 2024 - AMSTERDAM - CROSS-PLATFORM TRACKING WITH GOOGLE ANALYTICS.pptx
 
Ukraine War presentation: KNOW THE BASICS
Ukraine War presentation: KNOW THE BASICSUkraine War presentation: KNOW THE BASICS
Ukraine War presentation: KNOW THE BASICS
 
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
VIP High Class Call Girls Jamshedpur Anushka 8250192130 Independent Escort Se...
 
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls Punjabi Bagh 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
 
VIP Call Girls Service Charbagh { Lucknow Call Girls Service 9548273370 } Boo...
VIP Call Girls Service Charbagh { Lucknow Call Girls Service 9548273370 } Boo...VIP Call Girls Service Charbagh { Lucknow Call Girls Service 9548273370 } Boo...
VIP Call Girls Service Charbagh { Lucknow Call Girls Service 9548273370 } Boo...
 
Dubai Call Girls Wifey O52&786472 Call Girls Dubai
Dubai Call Girls Wifey O52&786472 Call Girls DubaiDubai Call Girls Wifey O52&786472 Call Girls Dubai
Dubai Call Girls Wifey O52&786472 Call Girls Dubai
 
04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationships04242024_CCC TUG_Joins and Relationships
04242024_CCC TUG_Joins and Relationships
 
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
꧁❤ Greater Noida Call Girls Delhi ❤꧂ 9711199171 ☎️ Hard And Sexy Vip Call
 
VIP High Class Call Girls Bikaner Anushka 8250192130 Independent Escort Servi...
VIP High Class Call Girls Bikaner Anushka 8250192130 Independent Escort Servi...VIP High Class Call Girls Bikaner Anushka 8250192130 Independent Escort Servi...
VIP High Class Call Girls Bikaner Anushka 8250192130 Independent Escort Servi...
 
Invezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signalsInvezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signals
 
High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...
High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...
High Class Call Girls Noida Sector 39 Aarushi 🔝8264348440🔝 Independent Escort...
 
Predicting Employee Churn: A Data-Driven Approach Project Presentation
Predicting Employee Churn: A Data-Driven Approach Project PresentationPredicting Employee Churn: A Data-Driven Approach Project Presentation
Predicting Employee Churn: A Data-Driven Approach Project Presentation
 
FESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdfFESE Capital Markets Fact Sheet 2024 Q1.pdf
FESE Capital Markets Fact Sheet 2024 Q1.pdf
 
Call Girls In Mahipalpur O9654467111 Escorts Service
Call Girls In Mahipalpur O9654467111  Escorts ServiceCall Girls In Mahipalpur O9654467111  Escorts Service
Call Girls In Mahipalpur O9654467111 Escorts Service
 
VIP Call Girls in Amravati Aarohi 8250192130 Independent Escort Service Amravati
VIP Call Girls in Amravati Aarohi 8250192130 Independent Escort Service AmravatiVIP Call Girls in Amravati Aarohi 8250192130 Independent Escort Service Amravati
VIP Call Girls in Amravati Aarohi 8250192130 Independent Escort Service Amravati
 
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip CallDelhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
Delhi Call Girls CP 9711199171 ☎✔👌✔ Whatsapp Hard And Sexy Vip Call
 
Brighton SEO | April 2024 | Data Storytelling
Brighton SEO | April 2024 | Data StorytellingBrighton SEO | April 2024 | Data Storytelling
Brighton SEO | April 2024 | Data Storytelling
 
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
Indian Call Girls in Abu Dhabi O5286O24O8 Call Girls in Abu Dhabi By Independ...
 
100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx
 
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.pptdokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
dokumen.tips_chapter-4-transient-heat-conduction-mehmet-kanoglu.ppt
 

151106 Sketch-based 3D Shape Retrievals using Convolutional Neural Networks

  • 1. Perception and Intelligence Laboratory Seoul National University Sketch-based 3D Shape Retrievals using Convolutional Neural Networks Fang Wang, Le Kang, Yi Li Junho Cho 15/11/06
  • 2. • Sketch-based 3D Shape Retrieval using Convolutional Neural Networks • CVPR 2015 oral • Retrieving 3D models from 2D sketches • http://users.cecs.anu.edu.au/~yili/ • Demo & code: http://users.cecs.anu.edu.au/~yili/cnnsbsr/ Perception and Intelligence Lab., Copyright © 2015 2 Introduction
  • 3. • Sketch-based is easy input, yet rich enough to specify shapes. • Early attempts: keywords, 3D shapes as queries • Directly matching 2D sketches to 3D model is difficult • Very different representations.. • Many methods 3D models projected to multiple 2D views. • Then match sketch to one of its views. • Variations in both sketch styles and 3D models  Low performance Perception and Intelligence Lab., Copyright © 2015 3 Introduction and Early attempts
  • 4. • Finding “Best views” for 3D model • Ideally, one of viewpoint similar to query sketch • Similarity score using Gabor, dense SIFT and GAILIF • No guarantee of best views have similar viewpoints with sketches. • Finding “Best view” is unsolved problem. • Elusive definition Perception and Intelligence Lab., Copyright © 2015 4 Early attempts
  • 5. 1. Propose to learn feature representations for sketch based shape retrieval, bypass dilemma of “Best view” selection. • Minimalism approach as opposed to multiple best views. • Just chose 2 views randomly in 3D model with hypothesis. • Still outperforms, showing features learned efficiently. 2. Two Siamese CNN to learn similarities in both within-domain and cross domain. • Sketches and views have distinctive intrinsic property. • Two different CNN models for sketch and model view. • Couples two input sources into the same target space. 3. Outperforms Perception and Intelligence Lab., Copyright © 2015 5 Contributions
  • 7. • CNN • CNN effectively learn complicated mappings from raw images to the target. • Less domain knowledge. (V.S. handcrafted features and shallow learning frameworks.) • Siamese Network • Two identical sub-convolutional networks. • Input as pairs of sample • Similar input pairs  similar output vectors • Dissimilar input pairs  dissimilar output vectors • Used in a weakly supervised metric learning setting. • Applied to text classification, speech feature classification, Face verification. Perception and Intelligence Lab., Copyright © 2015 7 CNN & Siamese Network
  • 8. Perception and Intelligence Lab., Copyright © 2015 8
  • 9. Perception and Intelligence Lab., Copyright © 2015 9 Learning a Similarity Measure Discriminatively Using a Siamese Network (S. Chopra, R. Hadsell, and Y. Lecun, CVPR2005)
  • 10. • Takes two samples, into separate but identical networks. • Typical loss function defined over pairs. • 𝑠1, 𝑠2 : two samples • 𝑦 : binary similarity label. Same 0, Different 1 • 𝐷 𝑤 =∥ 𝑓 𝑠1; 𝑤1 − 𝑓 𝑠2; 𝑤2 ∥1 : distance • Set 𝛼 = 1 𝐶 𝑝 , 𝛽 = 𝐶 𝑛, 𝛾 = − 2.77 𝐶 𝑛 , where 𝐶p = 0.2, Cn = 10 • Constants from Learning a Similarity Measure Discriminatively Using a Siamese Network • Input pairs labeled as similar  Bring output vectors closer. • Input pairs labeled as dissimilar  Push output vectors away. • Back-propagated gradients computed individually on two sample sets • Network updated by the average of two gradients Perception and Intelligence Lab., Copyright © 2015 10 Basic Siamese CNN
  • 11. Perception and Intelligence Lab., Copyright © 2015 11 𝑦=0 or 1 𝒚
  • 12. Learning feature representations for sketch based 3D shape retrieval
  • 13. Perception and Intelligence Lab., Copyright © 2015 13 Illustrated example of Cross-domain matching • Two domains: sketch & 3D models view • (a) Mixed • Learn correct mapping using pair similarities in each domain (s-s, v-v) as well as their cross-domain relations (s-v) jointly. • (b) Then two point sets correctly aligned in the feature space. • After cross domain metric learning, matching can be performed in sketch - sketch, view - view, sketch - view
  • 14. • Basic Siamese Network used for samples from the same domain. (ex s-s, v-v) • Cross domain setting, propose to extend it to two Siamese Networks, one for view domain, one for sketch domain • Define within-domain loss & cross domain loss • Better performance! (compared to Basic Siamese Network) Perception and Intelligence Lab., Copyright © 2015 14 Siamese Network for cross-domain matching
  • 15. • Loss function newly defined Sim of sketches Sim of views cross domain sim • 𝑠1, 𝑣1: sketch and view in same class • 𝑠2, 𝑣2: sketch and view in same class • 𝑦 : Binary similarity label. • L: • Actually, do not use category labels in the framework. • Possible description of desk? hand? face? doesn’t matter Perception and Intelligence Lab., Copyright © 2015 15 𝐿(𝑠1, 𝑣2, 𝑦)
  • 16. • Same network design for both networks, but learned separately. • Unlikely to basic Siamese Network. Perception and Intelligence Lab., Copyright © 2015 16
  • 17. • Only two views from 3D models. • Opposed to multiple views • 2 was enough • 1. Most of 3D models were up-right. 2. Two viewpoints randomly generated, angle difference larger than 45. • Didn’t focus on best view. Comparing views are beyond the scope of paper. • With chose viewpoint, generate 2D line drawings. 1. Closed boundaries 2. Suggestive Contours D.Decarlo. Suggestive contours for conveying shape Perception and Intelligence Lab., Copyright © 2015 17 View definitions and line drawing rendering
  • 19. • PSB / SBSR dataset • Widely used for 3D shape retrieval system evaluation • 1814 3D models • SBSR: 1814 hand drawn sketches collected using Amazon Mechanical Turk • SHREC’13 & ‘14 dataset • PSB Sketches in SBSR dataset not enough • Imbalanced number of sketches for classes • Can be biased • 1258 models, each 80 instances. • SHREC’14 greatly enlarged. 8987 3D models • Very hard • Models from various sources and arbitrarily oriented. Perception and Intelligence Lab., Copyright © 2015 19 Datasets
  • 20. 1. Precision-recall curve 2. mAP 3. Nearest Neighbor(NN) used to measure top 1 retrieval accuracy 4. E-Measure(E): harmonic mean of the precision and recall for the top 32 retrieval items 5. First/Second tier (FT/ST) and Discounted cumulated gain(DCG) as defined in the PSB statistics Perception and Intelligence Lab., Copyright © 2015 20 Evaluation criteria
  • 21. • Generating pairs for Siamese network • Reasonable proportion of similar and dissimilar pairs • Dissimilar pairs 10x more than similar pairs for successful training. • Randomly select 2 view pairs in the same category, • 20 view samples from other categories • Perform random paring for each training epoch. • Data augmentation for sketch set • Randomly performed affine transformations on sketch sample • Generate more variations on sketches • Two augmentation for each sketch sample. Perception and Intelligence Lab., Copyright © 2015 21 Experimental Settings
  • 22. • Siamese CNN based on Theano • 2.8GHz CPU and GTX 780 GPU • With preprocessed view features, retrieval time about 2 ms on SHREC’13 dataset • Training time proportional to total # of pairs and # of epochs. • 2.5 h for PSB/SBSR, 6 h for SHREC’13 • No significant performance gain when increasing views. 210 • Increased computational cost, GPU memory. • Two views are enough. Perception and Intelligence Lab., Copyright © 2015 22 Computational cost
  • 24. • Works very well on popular classes (human, face, plane) • Fine grained categorizations are difficult to distinguish • Shelf vs Box. only differ small. • Semantic ambiguity is very hard • Barn vs House. Differ in functionality. • Importance of viewpoint is decreased in this approach. • Plane, high degree of freedom, still retrieval results are excellent. Perception and Intelligence Lab., Copyright © 2015 24 Results on PSB/SBSR dataset
  • 25. • PSB/SBSR is very imbalanced dataset. • 71 classes are not in training set, only in test set. • Unseen classes can be retrievable? Ex) Unseen class • Even work well on failure case. (ex. flower  potting plant) • Demonstrates that it learns similarity effectively. Perception and Intelligence Lab., Copyright © 2015 25
  • 26. • Visualization of the learned features. • PCA on the features into 2D • Green dots: sketches • Yellow: views. • Similar shapes are grouped together automatically. • Animals, vehicles … Perception and Intelligence Lab., Copyright © 2015 26 Results on SHREC
  • 27. Perception and Intelligence Lab., Copyright © 2015 27
  • 28. Perception and Intelligence Lab., Copyright © 2015 28
  • 29. Perception and Intelligence Lab., Copyright © 2015 29
  • 30. Perception and Intelligence Lab., Copyright © 2015 30
  • 31. • Precision-recall curve • Outperforms. • 10% higher when small recall • Curve decreases much slower  More stable • 30% higher when recall reaches 1 Perception and Intelligence Lab., Copyright © 2015 31
  • 32. • Noticeable over-fitting in training. • Can be even better • Standard metrics for comparison • Performs better in every metric • Also compared with basic Siamese • Both sketches & views share the same network • Variations in two domains are different! Confirmed • Using same features(hand-crafted or learned) for both domains are bad. Perception and Intelligence Lab., Copyright © 2015 32
  • 33. • Within-domain retrieval • Already provided by dataset, but recheck the method. • View domain is more consistent than sketch domain • Inconsistency in sketch is the most challenging issue. • Powerful in learning features for both within-domain and cross-domain Perception and Intelligence Lab., Copyright © 2015 33
  • 34. • Proposed to learn feature presentations for sketch based 3D shape retrieval • Instead of computing “best views”, use predefined viewpoints and adopt two Siamese CNNs, one for views and one for sketches. • Bypass dilemma of best view selection • Experiments show the method is superior. Perception and Intelligence Lab., Copyright © 2015 34 Conclusion
  • 36. • 이거 자체가 learning cross domain similarities 로 해결해서 best views를 정 하는 이슈 없앰 • Minimalism approach as opposed to multiple best views. • 3D model 자체가 다 위로 생김. • 2개 이상 비교하는것보다 훨신 효과적임을 보임. • 이건 결국 feature을 제대로 학습했음을 보여줌. • Semantic level matching • Comprehensive shape represenations. Rather than combination of shllow features that only capture low level visual info Perception and Intelligence Lab., Copyright © 2015 36
  • 37. • Learn from CNN • Use Siamese Network. • Two input ousrces have distinctive intrinsic property  use 2 differenet CNN models. Sketch and model. • More power to capture different proporteis in idff domain. • Loss function to align the results of two CNN models. • Couples two input cources into the same targe tspace. • Compare features directly using a simple distance function. • Outperforms! Precision recall, NN1. retrievals in each domain effective, fast computation based on filtering. Perception and Intelligence Lab., Copyright © 2015 37
  • 38. • Stopping criteria. • All three of the datasets had been split into training and testing sets, but no validation set was specified. Therefore, we terminated our algorithm after 50 epochs for PSB/SBSR and 20 for SHREC’13 dataset (or until convergence). Multiple runs were performed and the mean values were reported. Perception and Intelligence Lab., Copyright © 2015 38 Experimental Settings
  • 39. Method dataset Measure 1 Measure 2 Measure 3 Measure 4 Baseline ABC 92 12 34 45 XXX ABC 32 32 54 76 YYY ABC 14 14 12 98 ZZZ ABC 32 23 32 67 Proposed ABC 14 42 41 87 Proposed (w.XX) ABC 32 15 35 67 Perception and Intelligence Lab., Copyright © 2015 39 Table example Table Title (if you want it to place here)
  • 40. Perception and Intelligence Lab., Copyright © 2015 40 Figure example < Updated cells > < CNN architecture > For highlight