SlideShare a Scribd company logo
1 of 21
Download to read offline
ConceptMap: Learning Visual Concepts
from Weakly-Labeled WWW images
A work by Eren Golge
Supervised by Asst. Prof. Pinar Duygulu
Dictionary
●
Visual Concept – a visual correspondence of semantic
values
– Objects (car, bus … ), attributes (red, metallic … ) or scenes
(indoor, kitchen, office …)
●
Polysemy – multiple semantic matching for a given
word
●
Model – Classifiers in Machine Learning sense
●
BoW – Bag of Words feature representation
Problems
●
Hard to have Large labeled data
●
Query Web sources : Google, Bing, Yahoo etc.
●
Evade polysemy or irrelevancy in the gathered data
●
Deal with Domain Adaptation
●
Learn salient models
●
Use lower concept models -objects- to discover higher level
concepts – scenes -
General Pipeline
GATHER DATA from
CLUSTER and
remove OUTLIERS
Learn Classifiers
Hassles
●
Polysemy
●
Irrelevancy
●
Data size
●
Model learning
Method #1 : CMAP
Polysemy : Clustering
Irrelevancy : Outlier detection+
Rectifying Self Organizing Map (RSOM)
Accepted for
Draft version : http://arxiv.org/abs/1312.4384
RSOM
●
Very Generic method for other domains as well (textual, biological etc.)
●
Extension of SOM (a.k.a. Kohonen's Map) *
●
Inspired by biological phenomenas **
●
Able to cluster data and detect outliers
●
IRRELEVANCY SOLVED!!
*Kohonen, T.: Self-organizing maps. Springer (1997)
**Hubel, D.H., Wiesel, T.N.: Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex. The Journal
of physiology 160(1) (1962) 106
Outlier clusters
Outlier instances in salient clusters
RSOM cont'
finding outlier units
●
Look activation statistics of each SOM unit in
learning phase
●
Latter learning iterations are more reliable
IF a unit is activated
REARLY → OUTLIER
FREQUENTLY → SALIENT
Winner activations Neighbor activations
RSOM cont'
finding sole outliers
x
x
x
x
Learning Models
●
Learn L1 linear SVM models
– Easier to train
– Better for high dimensional data
(wide data matrix)
– Implicit feature selection by L1
norm
●
Learn one linear model from each
salient cluster
●
Each concept has multiple models
– POLYSEMY SOLVED!!
CMAP Overview
Retrospective
●
Fergus et. al. [1]
– They use human annotated control set to cull data
– We use fully non-human afforded data
●
Berg and Forsyth [3]
– They use textual surrounding
– We use only visual content
●
OPTIMOL, Li and Fei-Fei [2]
– They use seed images and update incrementally
– We use no supervision with all in one iteration
●
Efros et. al. [4] “Discriminative Patches”
– They require a large computer clusters and iterative data elimination
– We use single computer with faster and better results and no time wasting iterations.
●
CMAP has broader possible applications
[1] Fergus, R., Fei-Fei, L., Perona, P., Zisserman, A.: Learning object categories from google’s image search. In: Computer Vision, 2005. ICCV 2005
[2] Berg, T.L., Berg, A.C., Edwards, J., Maire, M., White, R., Teh, Y.W., Learned-Miller, E.G., Forsyth, D.A.: Names and faces in the news. In: IEEE Conference on
Computer Vision
Pattern Recognition (CVPR). Volume 2. (2004) 848–854
[3] Li, L.J., Fei-Fei, L.: Optimol: automatic online picture collection via incremental model learning. International journal of computer vision 88(2) (2010) 147–168
[4] Singh, S., Gupta, A., Efros, A.A.: Unsupervised discovery of mid-level discriminative patches. In: Computer Vision–ECCV 2012. Springer (2012) 73–86
Experiments
●
Only use images for learning
●
Attack to problems:
– Attribute Learning : [1] , Images, Google [2],
[2]
●
Learn Texture and Color attributes
– Scene Learning : MIT-indoor [4], Scene-15 [5]
●
Use Attributes as mid-level features
– Face Recognition : FAN-Large [6]
●
Use EASY and HARD subset of the dataset
– Object Recognition : Google data-set [3]
[1] Russakovsky, O., Fei-Fei, L.: Attribute learning in large-scale datasets. In: Trends and Topics in Computer Vision. Springer (2012)
[2] Van De Weijer, J., Schmid, C., Verbeek, J., Larlus, D.: Learning color names for real-world applications. Image Processing, IEEE (2009)
[3] Fergus, R., Fei-Fei, L., Perona, P., Zisserman, A.: Learning object categories from google’s image search. In: Computer Vision, 2005. ICCV 2005
[4] Quattoni, A., Torralba, A.: Recognizing indoor scenes. CVPR (2009)
[5] Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. CVPR 2006
[6] Ozcan, M., Luo, J., Ferrari, V., Caputo, B.: A large-scale database of images and captions for automatic face naming. In: BMVC. (2011)
Visual Examples
Visual Examples # Faces
Salient Clusters Outlier Clusters Outlier Instances
Salient Clusters Outlier Clusters Outlier Instances
Implementation
●
Visual Features :
– BoW SIFT with 4000 words (for texture attribute, object and face)
– Use 3D 10x20x20 Lab Histograms (for attribute)
– 256 dimensional LBP [1] (for object and face)
●
Preprocessing
– Attribute: Extract random 100x100 non-overlapping image patches from each image.
– Scene: Represent each image with the confidence scores of attribute classifiers in a Spatial Pyramid sense
– Face: Apply face detection[2] to each image and get one highest score patch.
– Object: Apply unsupervised saliency detection [3] to images and get a single highest activation region.
●
Model Learning
– Use outliers and some sample of other concept instances as Negative set
– Apply Hard Mining
– Tune all hyper parameters via X-validation on the (classifiers and RSOM parameters)
●
NOTICE:
– We use Google images to train concept models and deal with DOMAIN ADAPTATION
[1] Ojala, T., Pietikainen, M., Maenpaa, T.: Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. Pattern Analysis and
Machine Intelligence, IEEE Transactions on 24(7) (2002) 971–987
[2] Zhu, X., Ramanan, D.: Face detection, pose estimation, and landmark localization in the wild. In: Computer Vision and Pattern Recognition (CVPR), 2012
IEEE Conference on, IEEE (2012) 2879–2886
[3] Erdem, E., Erdem, A.: Visual saliency estimation by nonlinearly integrating features using region covariances. Journal of Vision 13(4) (2013) 1–20
Results
Ours State of art
Face 0.66 0.58 [1]
Object 0.78 0.75 [2]
Attribute Image-Net 0.37 0.36 [3]
Attribute ebay 0.81 0.79 [4]
Attribute bing 0.82
-
- We beat all state of art methods except scene recognition!!
However our method is very cheaper compared to Li et al. [5]
[1] Ozcan, M., Luo, J., Ferrari, V., Caputo, B.: A large-scale database of images and captions for automatic face naming. BMVC. (2011)
[2] Fergus, R., Fei-Fei, L., Perona, P., Zisserman, A.: Learning object categories from google’s image search. In: Computer Vision, 2005. ICCV 2005
[3] Russakovsky, O., Fei-Fei, L.: Attribute learning in large-scale datasets. In: Trends and Topics in Computer Vision. Springer (2012)
[4] Van De Weijer, J., Schmid, C., Verbeek, J., Larlus, D.: Learning color names for real-world applications. Image Processing, IEEE (2009)
[5] Li, Q., Wu, J., Tu, Z.: Harvesting mid-level visual concepts from large-scale internet images. CVPR (2013)
Last Words
●
Fact – We propose a novel algorithm RSOM
●
Fact – Roughly beating all state-of-art methods
●
Fact – Solution for better data-sets with little or no
human effort
●
Improvement – Try to estimate # clusters implicitly
without any hyper parameter.
●
Improvement – Use more complex classification
scheme.
Not Much... Thanks for
valuable time :)

More Related Content

What's hot

Cross-domain complementary learning with synthetic data for multi-person part...
Cross-domain complementary learning with synthetic data for multi-person part...Cross-domain complementary learning with synthetic data for multi-person part...
Cross-domain complementary learning with synthetic data for multi-person part...哲东 郑
 
Project Face Detection
Project Face Detection Project Face Detection
Project Face Detection Abu Saleh Musa
 
Face Recognition Based on Deep Learning (Yurii Pashchenko Technology Stream)
Face Recognition Based on Deep Learning (Yurii Pashchenko Technology Stream) Face Recognition Based on Deep Learning (Yurii Pashchenko Technology Stream)
Face Recognition Based on Deep Learning (Yurii Pashchenko Technology Stream) IT Arena
 
Backbone can not be trained at once rolling back to pre trained network for p...
Backbone can not be trained at once rolling back to pre trained network for p...Backbone can not be trained at once rolling back to pre trained network for p...
Backbone can not be trained at once rolling back to pre trained network for p...NAVER Engineering
 
Image Search: Then and Now
Image Search: Then and NowImage Search: Then and Now
Image Search: Then and NowSi Krishan
 
Generative Models for General Audiences
Generative Models for General AudiencesGenerative Models for General Audiences
Generative Models for General AudiencesSangwoo Mo
 
Modern face recognition with deep learning
Modern face recognition with deep learningModern face recognition with deep learning
Modern face recognition with deep learningmarada0033
 
Image Processing Introduction
Image Processing IntroductionImage Processing Introduction
Image Processing IntroductionAhmed Gad
 
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
 
Moving object detection
Moving object detectionMoving object detection
Moving object detectionManav Mittal
 
Deep learning on face recognition (use case, development and risk)
Deep learning on face recognition (use case, development and risk)Deep learning on face recognition (use case, development and risk)
Deep learning on face recognition (use case, development and risk)Herman Kurnadi
 
Learning to learn unlearned feature for segmentation
Learning to learn unlearned feature for segmentationLearning to learn unlearned feature for segmentation
Learning to learn unlearned feature for segmentationNAVER Engineering
 
Adversarial Photo Frame: Concealing Sensitive Scene Information in a User-Acc...
Adversarial Photo Frame: Concealing Sensitive Scene Information in a User-Acc...Adversarial Photo Frame: Concealing Sensitive Scene Information in a User-Acc...
Adversarial Photo Frame: Concealing Sensitive Scene Information in a User-Acc...multimediaeval
 
A Hybrid Approach to Face Detection And Feature Extraction
A Hybrid Approach to Face Detection And Feature ExtractionA Hybrid Approach to Face Detection And Feature Extraction
A Hybrid Approach to Face Detection And Feature Extractioniosrjce
 
Deep learning for person re-identification
Deep learning for person re-identificationDeep learning for person re-identification
Deep learning for person re-identification哲东 郑
 
A survey on moving object tracking in video
A survey on moving object tracking in videoA survey on moving object tracking in video
A survey on moving object tracking in videoijitjournal
 
Introduction to Object recognition
Introduction to Object recognitionIntroduction to Object recognition
Introduction to Object recognitionAshiq Ullah
 
Domain Invariant Representation Learning with Domain Density Transformations
Domain Invariant Representation Learning with Domain Density TransformationsDomain Invariant Representation Learning with Domain Density Transformations
Domain Invariant Representation Learning with Domain Density TransformationsHyunKyu Jeon
 
Image–based face-detection-and-recognition-using-matlab
Image–based face-detection-and-recognition-using-matlabImage–based face-detection-and-recognition-using-matlab
Image–based face-detection-and-recognition-using-matlabIjcem Journal
 

What's hot (20)

Cross-domain complementary learning with synthetic data for multi-person part...
Cross-domain complementary learning with synthetic data for multi-person part...Cross-domain complementary learning with synthetic data for multi-person part...
Cross-domain complementary learning with synthetic data for multi-person part...
 
Project Face Detection
Project Face Detection Project Face Detection
Project Face Detection
 
Face Recognition Based on Deep Learning (Yurii Pashchenko Technology Stream)
Face Recognition Based on Deep Learning (Yurii Pashchenko Technology Stream) Face Recognition Based on Deep Learning (Yurii Pashchenko Technology Stream)
Face Recognition Based on Deep Learning (Yurii Pashchenko Technology Stream)
 
Backbone can not be trained at once rolling back to pre trained network for p...
Backbone can not be trained at once rolling back to pre trained network for p...Backbone can not be trained at once rolling back to pre trained network for p...
Backbone can not be trained at once rolling back to pre trained network for p...
 
Image Search: Then and Now
Image Search: Then and NowImage Search: Then and Now
Image Search: Then and Now
 
Generative Models for General Audiences
Generative Models for General AudiencesGenerative Models for General Audiences
Generative Models for General Audiences
 
Modern face recognition with deep learning
Modern face recognition with deep learningModern face recognition with deep learning
Modern face recognition with deep learning
 
Image Processing Introduction
Image Processing IntroductionImage Processing Introduction
Image Processing Introduction
 
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...
 
Moving object detection
Moving object detectionMoving object detection
Moving object detection
 
Deep learning on face recognition (use case, development and risk)
Deep learning on face recognition (use case, development and risk)Deep learning on face recognition (use case, development and risk)
Deep learning on face recognition (use case, development and risk)
 
Learning to learn unlearned feature for segmentation
Learning to learn unlearned feature for segmentationLearning to learn unlearned feature for segmentation
Learning to learn unlearned feature for segmentation
 
Adversarial Photo Frame: Concealing Sensitive Scene Information in a User-Acc...
Adversarial Photo Frame: Concealing Sensitive Scene Information in a User-Acc...Adversarial Photo Frame: Concealing Sensitive Scene Information in a User-Acc...
Adversarial Photo Frame: Concealing Sensitive Scene Information in a User-Acc...
 
A Hybrid Approach to Face Detection And Feature Extraction
A Hybrid Approach to Face Detection And Feature ExtractionA Hybrid Approach to Face Detection And Feature Extraction
A Hybrid Approach to Face Detection And Feature Extraction
 
Deep learning for person re-identification
Deep learning for person re-identificationDeep learning for person re-identification
Deep learning for person re-identification
 
A survey on moving object tracking in video
A survey on moving object tracking in videoA survey on moving object tracking in video
A survey on moving object tracking in video
 
Face Detection And Tracking
Face Detection And TrackingFace Detection And Tracking
Face Detection And Tracking
 
Introduction to Object recognition
Introduction to Object recognitionIntroduction to Object recognition
Introduction to Object recognition
 
Domain Invariant Representation Learning with Domain Density Transformations
Domain Invariant Representation Learning with Domain Density TransformationsDomain Invariant Representation Learning with Domain Density Transformations
Domain Invariant Representation Learning with Domain Density Transformations
 
Image–based face-detection-and-recognition-using-matlab
Image–based face-detection-and-recognition-using-matlabImage–based face-detection-and-recognition-using-matlab
Image–based face-detection-and-recognition-using-matlab
 

Similar to Cmap presentation

Recognizing Celebrity Faces in Lot of Web Images
Recognizing Celebrity Faces in Lot of Web ImagesRecognizing Celebrity Faces in Lot of Web Images
Recognizing Celebrity Faces in Lot of Web ImagesIJERA Editor
 
Real-time Face Detection and Recognition
Real-time Face Detection and RecognitionReal-time Face Detection and Recognition
Real-time Face Detection and RecognitionJia-Bin Huang
 
Face recognition Face Identification
Face recognition Face IdentificationFace recognition Face Identification
Face recognition Face IdentificationKalyan Acharjya
 
Face and facial expressions recognition for blind people
Face and facial expressions recognition for blind peopleFace and facial expressions recognition for blind people
Face and facial expressions recognition for blind peopleIRJET Journal
 
Face Annotation using Co-Relation based Matching for Improving Image Mining ...
Face Annotation using Co-Relation based Matching  for Improving Image Mining ...Face Annotation using Co-Relation based Matching  for Improving Image Mining ...
Face Annotation using Co-Relation based Matching for Improving Image Mining ...IRJET Journal
 
Gabriel Bianconi - Introduction to Face Processing with Computer Vision
Gabriel Bianconi - Introduction to Face Processing with Computer VisionGabriel Bianconi - Introduction to Face Processing with Computer Vision
Gabriel Bianconi - Introduction to Face Processing with Computer VisionPyCon Odessa
 
IRJET- Prediction of Facial Attribute without Landmark Information
IRJET-  	  Prediction of Facial Attribute without Landmark InformationIRJET-  	  Prediction of Facial Attribute without Landmark Information
IRJET- Prediction of Facial Attribute without Landmark InformationIRJET Journal
 
Visual Saliency Model Using Sift and Comparison of Learning Approaches
Visual Saliency Model Using Sift and Comparison of Learning ApproachesVisual Saliency Model Using Sift and Comparison of Learning Approaches
Visual Saliency Model Using Sift and Comparison of Learning Approachescsandit
 
IRJET - A Review on: Face Recognition using Laplacianface
IRJET - A Review on: Face Recognition using LaplacianfaceIRJET - A Review on: Face Recognition using Laplacianface
IRJET - A Review on: Face Recognition using LaplacianfaceIRJET Journal
 
Computer vision introduction
Computer vision  introduction Computer vision  introduction
Computer vision introduction Wael Badawy
 
IRJET - Automatic Attendance Provision using Image Processing
IRJET - Automatic Attendance Provision using Image ProcessingIRJET - Automatic Attendance Provision using Image Processing
IRJET - Automatic Attendance Provision using Image ProcessingIRJET Journal
 
Model Based Emotion Detection using Point Clouds
Model Based Emotion Detection using Point CloudsModel Based Emotion Detection using Point Clouds
Model Based Emotion Detection using Point CloudsLakshmi Sarvani Videla
 
Mining of Images Based on Structural Features Correlation for Facial Annotation
Mining of Images Based on Structural Features Correlation for Facial AnnotationMining of Images Based on Structural Features Correlation for Facial Annotation
Mining of Images Based on Structural Features Correlation for Facial AnnotationIRJET Journal
 
Burnaev and Notchenko. Skoltech. Bridging gap between 2D and 3D with Deep Lea...
Burnaev and Notchenko. Skoltech. Bridging gap between 2D and 3D with Deep Lea...Burnaev and Notchenko. Skoltech. Bridging gap between 2D and 3D with Deep Lea...
Burnaev and Notchenko. Skoltech. Bridging gap between 2D and 3D with Deep Lea...Skolkovo Robotics Center
 
Selective local binary pattern with convolutional neural network for facial ...
Selective local binary pattern with convolutional neural  network for facial ...Selective local binary pattern with convolutional neural  network for facial ...
Selective local binary pattern with convolutional neural network for facial ...IJECEIAES
 
Multilabel Image Retreval Using Hashing
Multilabel Image Retreval Using HashingMultilabel Image Retreval Using Hashing
Multilabel Image Retreval Using HashingSurbhi Bhosale
 
Multi Local Feature Selection Using Genetic Algorithm For Face Identification
Multi Local Feature Selection Using Genetic Algorithm For Face IdentificationMulti Local Feature Selection Using Genetic Algorithm For Face Identification
Multi Local Feature Selection Using Genetic Algorithm For Face IdentificationCSCJournals
 
Detecting Irregularities in the Shape of Coloured Bottle
Detecting Irregularities in the Shape of Coloured BottleDetecting Irregularities in the Shape of Coloured Bottle
Detecting Irregularities in the Shape of Coloured BottleIJERA Editor
 

Similar to Cmap presentation (20)

Recognizing Celebrity Faces in Lot of Web Images
Recognizing Celebrity Faces in Lot of Web ImagesRecognizing Celebrity Faces in Lot of Web Images
Recognizing Celebrity Faces in Lot of Web Images
 
Real-time Face Detection and Recognition
Real-time Face Detection and RecognitionReal-time Face Detection and Recognition
Real-time Face Detection and Recognition
 
Face recognition Face Identification
Face recognition Face IdentificationFace recognition Face Identification
Face recognition Face Identification
 
Face and facial expressions recognition for blind people
Face and facial expressions recognition for blind peopleFace and facial expressions recognition for blind people
Face and facial expressions recognition for blind people
 
Face Annotation using Co-Relation based Matching for Improving Image Mining ...
Face Annotation using Co-Relation based Matching  for Improving Image Mining ...Face Annotation using Co-Relation based Matching  for Improving Image Mining ...
Face Annotation using Co-Relation based Matching for Improving Image Mining ...
 
Gabriel Bianconi - Introduction to Face Processing with Computer Vision
Gabriel Bianconi - Introduction to Face Processing with Computer VisionGabriel Bianconi - Introduction to Face Processing with Computer Vision
Gabriel Bianconi - Introduction to Face Processing with Computer Vision
 
IRJET- Prediction of Facial Attribute without Landmark Information
IRJET-  	  Prediction of Facial Attribute without Landmark InformationIRJET-  	  Prediction of Facial Attribute without Landmark Information
IRJET- Prediction of Facial Attribute without Landmark Information
 
Visual Saliency Model Using Sift and Comparison of Learning Approaches
Visual Saliency Model Using Sift and Comparison of Learning ApproachesVisual Saliency Model Using Sift and Comparison of Learning Approaches
Visual Saliency Model Using Sift and Comparison of Learning Approaches
 
IRJET - A Review on: Face Recognition using Laplacianface
IRJET - A Review on: Face Recognition using LaplacianfaceIRJET - A Review on: Face Recognition using Laplacianface
IRJET - A Review on: Face Recognition using Laplacianface
 
Computer vision introduction
Computer vision  introduction Computer vision  introduction
Computer vision introduction
 
IRJET - Automatic Attendance Provision using Image Processing
IRJET - Automatic Attendance Provision using Image ProcessingIRJET - Automatic Attendance Provision using Image Processing
IRJET - Automatic Attendance Provision using Image Processing
 
Model Based Emotion Detection using Point Clouds
Model Based Emotion Detection using Point CloudsModel Based Emotion Detection using Point Clouds
Model Based Emotion Detection using Point Clouds
 
Mining of Images Based on Structural Features Correlation for Facial Annotation
Mining of Images Based on Structural Features Correlation for Facial AnnotationMining of Images Based on Structural Features Correlation for Facial Annotation
Mining of Images Based on Structural Features Correlation for Facial Annotation
 
Burnaev and Notchenko. Skoltech. Bridging gap between 2D and 3D with Deep Lea...
Burnaev and Notchenko. Skoltech. Bridging gap between 2D and 3D with Deep Lea...Burnaev and Notchenko. Skoltech. Bridging gap between 2D and 3D with Deep Lea...
Burnaev and Notchenko. Skoltech. Bridging gap between 2D and 3D with Deep Lea...
 
Real time facial expression analysis using pca
Real time facial expression analysis using pcaReal time facial expression analysis using pca
Real time facial expression analysis using pca
 
Selective local binary pattern with convolutional neural network for facial ...
Selective local binary pattern with convolutional neural  network for facial ...Selective local binary pattern with convolutional neural  network for facial ...
Selective local binary pattern with convolutional neural network for facial ...
 
Multilabel Image Retreval Using Hashing
Multilabel Image Retreval Using HashingMultilabel Image Retreval Using Hashing
Multilabel Image Retreval Using Hashing
 
50120140504002
5012014050400250120140504002
50120140504002
 
Multi Local Feature Selection Using Genetic Algorithm For Face Identification
Multi Local Feature Selection Using Genetic Algorithm For Face IdentificationMulti Local Feature Selection Using Genetic Algorithm For Face Identification
Multi Local Feature Selection Using Genetic Algorithm For Face Identification
 
Detecting Irregularities in the Shape of Coloured Bottle
Detecting Irregularities in the Shape of Coloured BottleDetecting Irregularities in the Shape of Coloured Bottle
Detecting Irregularities in the Shape of Coloured Bottle
 

Recently uploaded

All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...Sérgio Sacani
 
Is RISC-V ready for HPC workload? Maybe?
Is RISC-V ready for HPC workload? Maybe?Is RISC-V ready for HPC workload? Maybe?
Is RISC-V ready for HPC workload? Maybe?Patrick Diehl
 
Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.aasikanpl
 
Animal Communication- Auditory and Visual.pptx
Animal Communication- Auditory and Visual.pptxAnimal Communication- Auditory and Visual.pptx
Animal Communication- Auditory and Visual.pptxUmerFayaz5
 
A relative description on Sonoporation.pdf
A relative description on Sonoporation.pdfA relative description on Sonoporation.pdf
A relative description on Sonoporation.pdfnehabiju2046
 
Hubble Asteroid Hunter III. Physical properties of newly found asteroids
Hubble Asteroid Hunter III. Physical properties of newly found asteroidsHubble Asteroid Hunter III. Physical properties of newly found asteroids
Hubble Asteroid Hunter III. Physical properties of newly found asteroidsSérgio Sacani
 
Caco-2 cell permeability assay for drug absorption
Caco-2 cell permeability assay for drug absorptionCaco-2 cell permeability assay for drug absorption
Caco-2 cell permeability assay for drug absorptionPriyansha Singh
 
Recombinant DNA technology (Immunological screening)
Recombinant DNA technology (Immunological screening)Recombinant DNA technology (Immunological screening)
Recombinant DNA technology (Immunological screening)PraveenaKalaiselvan1
 
SOLUBLE PATTERN RECOGNITION RECEPTORS.pptx
SOLUBLE PATTERN RECOGNITION RECEPTORS.pptxSOLUBLE PATTERN RECOGNITION RECEPTORS.pptx
SOLUBLE PATTERN RECOGNITION RECEPTORS.pptxkessiyaTpeter
 
Spermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatidSpermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatidSarthak Sekhar Mondal
 
Botany 4th semester file By Sumit Kumar yadav.pdf
Botany 4th semester file By Sumit Kumar yadav.pdfBotany 4th semester file By Sumit Kumar yadav.pdf
Botany 4th semester file By Sumit Kumar yadav.pdfSumit Kumar yadav
 
Biological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfBiological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfmuntazimhurra
 
Nanoparticles synthesis and characterization​ ​
Nanoparticles synthesis and characterization​  ​Nanoparticles synthesis and characterization​  ​
Nanoparticles synthesis and characterization​ ​kaibalyasahoo82800
 
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...Lokesh Kothari
 
Bentham & Hooker's Classification. along with the merits and demerits of the ...
Bentham & Hooker's Classification. along with the merits and demerits of the ...Bentham & Hooker's Classification. along with the merits and demerits of the ...
Bentham & Hooker's Classification. along with the merits and demerits of the ...Nistarini College, Purulia (W.B) India
 
Grafana in space: Monitoring Japan's SLIM moon lander in real time
Grafana in space: Monitoring Japan's SLIM moon lander  in real timeGrafana in space: Monitoring Japan's SLIM moon lander  in real time
Grafana in space: Monitoring Japan's SLIM moon lander in real timeSatoshi NAKAHIRA
 
Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...
Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...
Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...jana861314
 

Recently uploaded (20)

All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...
All-domain Anomaly Resolution Office U.S. Department of Defense (U) Case: “Eg...
 
Is RISC-V ready for HPC workload? Maybe?
Is RISC-V ready for HPC workload? Maybe?Is RISC-V ready for HPC workload? Maybe?
Is RISC-V ready for HPC workload? Maybe?
 
Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
 
Animal Communication- Auditory and Visual.pptx
Animal Communication- Auditory and Visual.pptxAnimal Communication- Auditory and Visual.pptx
Animal Communication- Auditory and Visual.pptx
 
A relative description on Sonoporation.pdf
A relative description on Sonoporation.pdfA relative description on Sonoporation.pdf
A relative description on Sonoporation.pdf
 
Hubble Asteroid Hunter III. Physical properties of newly found asteroids
Hubble Asteroid Hunter III. Physical properties of newly found asteroidsHubble Asteroid Hunter III. Physical properties of newly found asteroids
Hubble Asteroid Hunter III. Physical properties of newly found asteroids
 
Caco-2 cell permeability assay for drug absorption
Caco-2 cell permeability assay for drug absorptionCaco-2 cell permeability assay for drug absorption
Caco-2 cell permeability assay for drug absorption
 
Recombinant DNA technology (Immunological screening)
Recombinant DNA technology (Immunological screening)Recombinant DNA technology (Immunological screening)
Recombinant DNA technology (Immunological screening)
 
SOLUBLE PATTERN RECOGNITION RECEPTORS.pptx
SOLUBLE PATTERN RECOGNITION RECEPTORS.pptxSOLUBLE PATTERN RECOGNITION RECEPTORS.pptx
SOLUBLE PATTERN RECOGNITION RECEPTORS.pptx
 
Spermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatidSpermiogenesis or Spermateleosis or metamorphosis of spermatid
Spermiogenesis or Spermateleosis or metamorphosis of spermatid
 
Botany 4th semester file By Sumit Kumar yadav.pdf
Botany 4th semester file By Sumit Kumar yadav.pdfBotany 4th semester file By Sumit Kumar yadav.pdf
Botany 4th semester file By Sumit Kumar yadav.pdf
 
Biological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdfBiological Classification BioHack (3).pdf
Biological Classification BioHack (3).pdf
 
The Philosophy of Science
The Philosophy of ScienceThe Philosophy of Science
The Philosophy of Science
 
Nanoparticles synthesis and characterization​ ​
Nanoparticles synthesis and characterization​  ​Nanoparticles synthesis and characterization​  ​
Nanoparticles synthesis and characterization​ ​
 
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
 
9953056974 Young Call Girls In Mahavir enclave Indian Quality Escort service
9953056974 Young Call Girls In Mahavir enclave Indian Quality Escort service9953056974 Young Call Girls In Mahavir enclave Indian Quality Escort service
9953056974 Young Call Girls In Mahavir enclave Indian Quality Escort service
 
CELL -Structural and Functional unit of life.pdf
CELL -Structural and Functional unit of life.pdfCELL -Structural and Functional unit of life.pdf
CELL -Structural and Functional unit of life.pdf
 
Bentham & Hooker's Classification. along with the merits and demerits of the ...
Bentham & Hooker's Classification. along with the merits and demerits of the ...Bentham & Hooker's Classification. along with the merits and demerits of the ...
Bentham & Hooker's Classification. along with the merits and demerits of the ...
 
Grafana in space: Monitoring Japan's SLIM moon lander in real time
Grafana in space: Monitoring Japan's SLIM moon lander  in real timeGrafana in space: Monitoring Japan's SLIM moon lander  in real time
Grafana in space: Monitoring Japan's SLIM moon lander in real time
 
Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...
Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...
Traditional Agroforestry System in India- Shifting Cultivation, Taungya, Home...
 

Cmap presentation

  • 1. ConceptMap: Learning Visual Concepts from Weakly-Labeled WWW images A work by Eren Golge Supervised by Asst. Prof. Pinar Duygulu
  • 2. Dictionary ● Visual Concept – a visual correspondence of semantic values – Objects (car, bus … ), attributes (red, metallic … ) or scenes (indoor, kitchen, office …) ● Polysemy – multiple semantic matching for a given word ● Model – Classifiers in Machine Learning sense ● BoW – Bag of Words feature representation
  • 3. Problems ● Hard to have Large labeled data ● Query Web sources : Google, Bing, Yahoo etc. ● Evade polysemy or irrelevancy in the gathered data ● Deal with Domain Adaptation ● Learn salient models ● Use lower concept models -objects- to discover higher level concepts – scenes -
  • 4. General Pipeline GATHER DATA from CLUSTER and remove OUTLIERS Learn Classifiers
  • 6. Method #1 : CMAP Polysemy : Clustering Irrelevancy : Outlier detection+ Rectifying Self Organizing Map (RSOM) Accepted for Draft version : http://arxiv.org/abs/1312.4384
  • 7. RSOM ● Very Generic method for other domains as well (textual, biological etc.) ● Extension of SOM (a.k.a. Kohonen's Map) * ● Inspired by biological phenomenas ** ● Able to cluster data and detect outliers ● IRRELEVANCY SOLVED!! *Kohonen, T.: Self-organizing maps. Springer (1997) **Hubel, D.H., Wiesel, T.N.: Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex. The Journal of physiology 160(1) (1962) 106 Outlier clusters Outlier instances in salient clusters
  • 8. RSOM cont' finding outlier units ● Look activation statistics of each SOM unit in learning phase ● Latter learning iterations are more reliable IF a unit is activated REARLY → OUTLIER FREQUENTLY → SALIENT Winner activations Neighbor activations
  • 9. RSOM cont' finding sole outliers x x x x
  • 10. Learning Models ● Learn L1 linear SVM models – Easier to train – Better for high dimensional data (wide data matrix) – Implicit feature selection by L1 norm ● Learn one linear model from each salient cluster ● Each concept has multiple models – POLYSEMY SOLVED!!
  • 12. Retrospective ● Fergus et. al. [1] – They use human annotated control set to cull data – We use fully non-human afforded data ● Berg and Forsyth [3] – They use textual surrounding – We use only visual content ● OPTIMOL, Li and Fei-Fei [2] – They use seed images and update incrementally – We use no supervision with all in one iteration ● Efros et. al. [4] “Discriminative Patches” – They require a large computer clusters and iterative data elimination – We use single computer with faster and better results and no time wasting iterations. ● CMAP has broader possible applications [1] Fergus, R., Fei-Fei, L., Perona, P., Zisserman, A.: Learning object categories from google’s image search. In: Computer Vision, 2005. ICCV 2005 [2] Berg, T.L., Berg, A.C., Edwards, J., Maire, M., White, R., Teh, Y.W., Learned-Miller, E.G., Forsyth, D.A.: Names and faces in the news. In: IEEE Conference on Computer Vision Pattern Recognition (CVPR). Volume 2. (2004) 848–854 [3] Li, L.J., Fei-Fei, L.: Optimol: automatic online picture collection via incremental model learning. International journal of computer vision 88(2) (2010) 147–168 [4] Singh, S., Gupta, A., Efros, A.A.: Unsupervised discovery of mid-level discriminative patches. In: Computer Vision–ECCV 2012. Springer (2012) 73–86
  • 13. Experiments ● Only use images for learning ● Attack to problems: – Attribute Learning : [1] , Images, Google [2], [2] ● Learn Texture and Color attributes – Scene Learning : MIT-indoor [4], Scene-15 [5] ● Use Attributes as mid-level features – Face Recognition : FAN-Large [6] ● Use EASY and HARD subset of the dataset – Object Recognition : Google data-set [3] [1] Russakovsky, O., Fei-Fei, L.: Attribute learning in large-scale datasets. In: Trends and Topics in Computer Vision. Springer (2012) [2] Van De Weijer, J., Schmid, C., Verbeek, J., Larlus, D.: Learning color names for real-world applications. Image Processing, IEEE (2009) [3] Fergus, R., Fei-Fei, L., Perona, P., Zisserman, A.: Learning object categories from google’s image search. In: Computer Vision, 2005. ICCV 2005 [4] Quattoni, A., Torralba, A.: Recognizing indoor scenes. CVPR (2009) [5] Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. CVPR 2006 [6] Ozcan, M., Luo, J., Ferrari, V., Caputo, B.: A large-scale database of images and captions for automatic face naming. In: BMVC. (2011)
  • 15.
  • 16. Visual Examples # Faces Salient Clusters Outlier Clusters Outlier Instances
  • 17. Salient Clusters Outlier Clusters Outlier Instances
  • 18. Implementation ● Visual Features : – BoW SIFT with 4000 words (for texture attribute, object and face) – Use 3D 10x20x20 Lab Histograms (for attribute) – 256 dimensional LBP [1] (for object and face) ● Preprocessing – Attribute: Extract random 100x100 non-overlapping image patches from each image. – Scene: Represent each image with the confidence scores of attribute classifiers in a Spatial Pyramid sense – Face: Apply face detection[2] to each image and get one highest score patch. – Object: Apply unsupervised saliency detection [3] to images and get a single highest activation region. ● Model Learning – Use outliers and some sample of other concept instances as Negative set – Apply Hard Mining – Tune all hyper parameters via X-validation on the (classifiers and RSOM parameters) ● NOTICE: – We use Google images to train concept models and deal with DOMAIN ADAPTATION [1] Ojala, T., Pietikainen, M., Maenpaa, T.: Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. Pattern Analysis and Machine Intelligence, IEEE Transactions on 24(7) (2002) 971–987 [2] Zhu, X., Ramanan, D.: Face detection, pose estimation, and landmark localization in the wild. In: Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, IEEE (2012) 2879–2886 [3] Erdem, E., Erdem, A.: Visual saliency estimation by nonlinearly integrating features using region covariances. Journal of Vision 13(4) (2013) 1–20
  • 19. Results Ours State of art Face 0.66 0.58 [1] Object 0.78 0.75 [2] Attribute Image-Net 0.37 0.36 [3] Attribute ebay 0.81 0.79 [4] Attribute bing 0.82 - - We beat all state of art methods except scene recognition!! However our method is very cheaper compared to Li et al. [5] [1] Ozcan, M., Luo, J., Ferrari, V., Caputo, B.: A large-scale database of images and captions for automatic face naming. BMVC. (2011) [2] Fergus, R., Fei-Fei, L., Perona, P., Zisserman, A.: Learning object categories from google’s image search. In: Computer Vision, 2005. ICCV 2005 [3] Russakovsky, O., Fei-Fei, L.: Attribute learning in large-scale datasets. In: Trends and Topics in Computer Vision. Springer (2012) [4] Van De Weijer, J., Schmid, C., Verbeek, J., Larlus, D.: Learning color names for real-world applications. Image Processing, IEEE (2009) [5] Li, Q., Wu, J., Tu, Z.: Harvesting mid-level visual concepts from large-scale internet images. CVPR (2013)
  • 20. Last Words ● Fact – We propose a novel algorithm RSOM ● Fact – Roughly beating all state-of-art methods ● Fact – Solution for better data-sets with little or no human effort ● Improvement – Try to estimate # clusters implicitly without any hyper parameter. ● Improvement – Use more complex classification scheme.
  • 21. Not Much... Thanks for valuable time :)