Universitat Politècnica de Catalunya, profile picture
Uploaded byUniversitat Politècnica de Catalunya
PDF, PPTX719 views

Curriculum Learning for Recurrent Video Object Segmentation

The document discusses curriculum learning applied to recurrent video object segmentation, presenting a methodology where training data is introduced progressively from simple to complex concepts. It explores the Kitti-MOTS dataset, describing an end-to-end recurrent network model for video object segmentation, along with various experimental setups and evaluation metrics. The conclusions highlight the importance of dataset understanding and suggest directions for future work, including further adjustments to training techniques.

Embed presentation

Download as PDF, PPTX
1 / 144
2 / 144
3 / 144
4 / 144
5 / 144
6 / 144
7 / 144
8 / 144
9 / 144
10 / 144
11 / 144
12 / 144
13 / 144
14 / 144
15 / 144
16 / 144
17 / 144
18 / 144
19 / 144
20 / 144
21 / 144
22 / 144
23 / 144
24 / 144
25 / 144
26 / 144
27 / 144
28 / 144
29 / 144
30 / 144
31 / 144
32 / 144
33 / 144
34 / 144
35 / 144
36 / 144
37 / 144
38 / 144
39 / 144
40 / 144
41 / 144
42 / 144
43 / 144
44 / 144
45 / 144
46 / 144
47 / 144
48 / 144
49 / 144
50 / 144
51 / 144
52 / 144
53 / 144
54 / 144
55 / 144
56 / 144
57 / 144
58 / 144
59 / 144
60 / 144
61 / 144
62 / 144
63 / 144
64 / 144
65 / 144
66 / 144
67 / 144
68 / 144
69 / 144
70 / 144
71 / 144
72 / 144
73 / 144
74 / 144
75 / 144
76 / 144
77 / 144
78 / 144
79 / 144
80 / 144
81 / 144
82 / 144
83 / 144
84 / 144
85 / 144
86 / 144
87 / 144
88 / 144
89 / 144
90 / 144
91 / 144
92 / 144
93 / 144
94 / 144
95 / 144
96 / 144
97 / 144
98 / 144
99 / 144
100 / 144
101 / 144
102 / 144
103 / 144
104 / 144
105 / 144
106 / 144
107 / 144
108 / 144
109 / 144
110 / 144
111 / 144
112 / 144
113 / 144
114 / 144
115 / 144
116 / 144
117 / 144
118 / 144
119 / 144
120 / 144
121 / 144
122 / 144
123 / 144
124 / 144
125 / 144
126 / 144
127 / 144
128 / 144
129 / 144
130 / 144
131 / 144
132 / 144
133 / 144
134 / 144
135 / 144
136 / 144
137 / 144
138 / 144
139 / 144
140 / 144
141 / 144
142 / 144
143 / 144
144 / 144
CURRICULUM LEARNING FOR RECURRENT VIDEO OBJECT SEGMENTATION Co-directors: Xavier Giró Nieto and Carles Ventura Royo Author: Maria Gonzàlez Calabuig
Introduction Dataset The model Experiment sets Techniques Qualitative results YouTube-VOS Conclusions CONTENTS
INTRODUCTION
INTRODUCTION Curriculum Learning for Recurrent VOS - 4 of 144 Curriculum Learning: Methodology inspired by the learning process of humans. The training data is presented in a meaningful way, from simple to complex concepts. Yoshua Bengio et al. “Curriculum Learning”, ICML. 2019.
INTRODUCTION Curriculum Learning for Recurrent VOS - 5 of 144 Curriculum Learning: Methodology inspired by the learning process of humans. The training data is presented in a meaningful way, from simple to complex concepts. 4 curriculums Yoshua Bengio et al. “Curriculum Learning”, ICML. 2019.
INTRODUCTION Curriculum Learning for Recurrent VOS - 6 of 144 Curriculum Learning: Methodology inspired by the learning process of humans. The training data is presented in a meaningful way, from simple to complex concepts. 4 curriculums THE DATASET Yoshua Bengio et al. “Curriculum Learning”, ICML. 2019.
INTRODUCTION Curriculum Learning for Recurrent VOS - 7 of 144 Curriculum Learning: Methodology inspired by the learning process of humans. The training data is presented in a meaningful way, from simple to complex concepts. 4 curriculums THE DATASET THE MODEL Yoshua Bengio et al. “Curriculum Learning”, ICML. 2019.
INTRODUCTION Curriculum Learning for Recurrent VOS - 8 of 144 THE TASK Semi-supervised or “one-shot” Video Object Segmentation
INTRODUCTION Curriculum Learning for Recurrent VOS - 9 of 144 THE TASK Semi-supervised or “one-shot” Video Object Segmentation
INTRODUCTION Curriculum Learning for Recurrent VOS - 10 of 144 THE TASK Semi-supervised or “one-shot” Video Object Segmentation
INTRODUCTION Curriculum Learning for Recurrent VOS - 11 of 144 THE TASK Estimated by the modelGiven to the model Semi-supervised or “one-shot” Video Object Segmentation
DATASET
KITTI-MOTS DATASET Curriculum Learning for Recurrent VOS - 13 of 144 Andreas Geiger, Philip Lenz, and Raquel Urtasun. “Are we ready for Autonomous Driving? The KITTI Vision Benchmark Suite”, CVPR 2012.
KITTI-MOTS DATASET Curriculum Learning for Recurrent VOS - 14 of 144 Andreas Geiger, Philip Lenz, and Raquel Urtasun. “Are we ready for Autonomous Driving? The KITTI Vision Benchmark Suite”, CVPR 2012. Its video sequences present challenges:
KITTI-MOTS DATASET Curriculum Learning for Recurrent VOS - 15 of 144 Its video sequences present challenges: Andreas Geiger, Philip Lenz, and Raquel Urtasun. “Are we ready for Autonomous Driving? The KITTI Vision Benchmark Suite”, CVPR 2012.
KITTI-MOTS DATASET Curriculum Learning for Recurrent VOS - 16 of 144 Its video sequences present challenges: Andreas Geiger, Philip Lenz, and Raquel Urtasun. “Are we ready for Autonomous Driving? The KITTI Vision Benchmark Suite”, CVPR 2012.
KITTI-MOTS DATASET Curriculum Learning for Recurrent VOS - 17 of 144 Its video sequences present challenges: Andreas Geiger, Philip Lenz, and Raquel Urtasun. “Are we ready for Autonomous Driving? The KITTI Vision Benchmark Suite”, CVPR 2012.
THE MODEL
THE MODEL End-to-End Recurrent Network for video object segmentation: RVOS Curriculum Learning for Recurrent VOS - 19 of 144 Carles Ventura, Miriam Bellver, Andreu Girbau, Amaia Salvador, Ferran Marques and Xavier Giro-i-Nieto. “RVOS: End-to-End Recurrent Network for Video Object Segmentation”, CVPR 2019.
THE MODEL End-to-End Recurrent Network for video object segmentation: RVOS Curriculum Learning for Recurrent VOS - 20 of 144 Athar, A., Mahadevan, S., Oˇsep, A., Leal-Taix´e, L., Leibe, B.: Stem-seg: Spatio-temporal embeddings for instance segmentation in videos., ECCV (2020)
EXPERIMENT SETS
SETS OF EXPERIMENTS All techniques tested on two sets of experiments: Resolution Batch Size Length clip 287x950 2 3 Resolution Batch Size Length clip 256x448 4 5 Curriculum Learning for Recurrent VOS - 22 of 144
METRICS The results have been evaluated on the official metrics of the MOTS Challenge. - sMOTSA has been defined as the reference metric: Curriculum Learning for Recurrent VOS - 23 of 144 Paul Voigtlaender et al. “MOTS: Multi-Object Tracking and Segmentation”, CVPR 2019.
METRICS The results have been evaluated on the official metrics of the MOTS Challenge. - sMOTSA has been defined as the reference metric: Curriculum Learning for Recurrent VOS - 25 of 144 Paul Voigtlaender et al. “MOTS: Multi-Object Tracking and Segmentation”, CVPR 2019.
EVALUATION METHOD Proposal: Evaluation averaged per sequence Curriculum Learning for Recurrent VOS - 25 of 144 Sequences
SCHEDULE SAMPLING
SCHEDULE SAMPLING Curriculum Learning for Recurrent VOS - 27 of 144 VOS requires information about the previous step.
SCHEDULE SAMPLING Curriculum Learning for Recurrent VOS - 28 of 144 Train using the model’s outputs.
SCHEDULE SAMPLING Curriculum Learning for Recurrent VOS - 29 of 144 Train using the ground-truth annotations.
SCHEDULE SAMPLING Curriculum Learning for Recurrent VOS - 30 of 144 TEACHER FORCING
SCHEDULE SAMPLING Curriculum Learning for Recurrent VOS - 31 of 144 TEACHER FORCING Fast and efficient
SCHEDULE SAMPLING Curriculum Learning for Recurrent VOS - 32 of 144 TEACHER FORCING Fast and efficient Leads to exposure bias
SCHEDULE SAMPLING Curriculum Learning for Recurrent VOS - 33 of 144 time
SCHEDULE SAMPLING Curriculum Learning for Recurrent VOS - 34 of 144 time
Schedule Sampling SCHEDULE SAMPLING Curriculum Learning for Recurrent VOS - 35 of 144
Schedule Sampling Linear SCHEDULE SAMPLING Curriculum Learning for Recurrent VOS - 36 of 144
Schedule Sampling Linear Step SCHEDULE SAMPLING Curriculum Learning for Recurrent VOS - 37 of 144
Schedule Sampling Linear Forward Step Forward SCHEDULE SAMPLING Curriculum Learning for Recurrent VOS - 38 of 144
Schedule Sampling Linear Forward Step Forward SCHEDULE SAMPLING Curriculum Learning for Recurrent VOS - 39 of 144
Schedule Sampling Linear Forward Step Forward SCHEDULE SAMPLING Curriculum Learning for Recurrent VOS - 40 of 144
Schedule Sampling Linear Forward Inverse Step Forward Inverse SCHEDULE SAMPLING Curriculum Learning for Recurrent VOS - 41 of 144
Schedule Sampling Linear Forward Inverse Step Forward Inverse SCHEDULE SAMPLING Curriculum Learning for Recurrent VOS - 42 of 144
Schedule Sampling Linear Forward Inverse Step Forward Inverse SCHEDULE SAMPLING Curriculum Learning for Recurrent VOS - 43 of 144
Schedule Sampling Linear Forward Inverse Step Forward Inverse SCHEDULE SAMPLING Curriculum Learning for Recurrent VOS - 44 of 144
SCHEDULE SAMPLING Curriculum Learning for Recurrent VOS - 45 of 144 RESULTS ON THE FORWARD STRATEGIES
SCHEDULE SAMPLING Curriculum Learning for Recurrent VOS - 46 of 144 RESULTS ON THE INVERSE STRATEGIES
SCHEDULE SAMPLING Curriculum Learning for Recurrent VOS - 47 of 144 OVERVIEW
SCHEDULE SAMPLING Curriculum Learning for Recurrent VOS - 48 of 144 OVERVIEW
SCHEDULE SAMPLING Curriculum Learning for Recurrent VOS - 49 of 144 OVERVIEW
SCHEDULE SAMPLING Curriculum Learning for Recurrent VOS - 50 of 144 OVERVIEW
FRAME SKIPPING
FRAME SKIPPING Curriculum Learning for Recurrent VOS - 52 of 144 KITTI-MOTS has slow-motion video sequences. frame #1
FRAME SKIPPING Curriculum Learning for Recurrent VOS - 53 of 144 KITTI-MOTS has slow-motion video sequences. frame #1 frame #2
FRAME SKIPPING Curriculum Learning for Recurrent VOS - 54 of 144 KITTI-MOTS has slow-motion video sequences. frame #1 frame #2 frame #3
FRAME SKIPPING Curriculum Learning for Recurrent VOS - 55 of 144 KITTI-MOTS has slow-motion video sequences. frame #1 frame #2 frame #3 frame #4
FRAME SKIPPING Curriculum Learning for Recurrent VOS - 56 of 144 KITTI-MOTS has slow-motion video sequences. frame #1 frame #2 frame #3 frame #4 frame #5
FRAME SKIPPING Curriculum Learning for Recurrent VOS - 57 of 144 KITTI-MOTS has slow-motion video sequences. frame #1 frame #2 frame #3 frame #4 frame #5 frame #6
FRAME SKIPPING Curriculum Learning for Recurrent VOS - 58 of 144 Ideally: … ... . … … .. N fram es of the sequence
FRAME SKIPPING Curriculum Learning for Recurrent VOS - 59 of 144 Ideally: But we have limitations (e.g. memory constraints) … … .. N fram es of the sequence … ... .
FRAME SKIPPING Curriculum Learning for Recurrent VOS - 60 of 144
FRAME SKIPPING Curriculum Learning for Recurrent VOS - 61 of 144
FRAME SKIPPING Frame Skipping Curriculum Learning for Recurrent VOS - 62 of 144
FRAME SKIPPING Frame Skipping From 0 to 9 Curriculum Learning for Recurrent VOS - 63 of 144
FRAME SKIPPING Frame Skipping From 0 to 9 Curriculum Learning for Recurrent VOS - 64 of 144 time
FRAME SKIPPING Frame Skipping From 0 to 9 Curriculum Learning for Recurrent VOS - 65 of 144 time
FRAME SKIPPING Frame Skipping From 0 to 9 Curriculum Learning for Recurrent VOS - 66 of 144 time
FRAME SKIPPING Frame Skipping From 0 to 9 Curriculum Learning for Recurrent VOS - 67 of 144 time ...
FRAME SKIPPING Frame Skipping From 0 to 9 From 1 to 5 Curriculum Learning for Recurrent VOS - 68 of 144 time
FRAME SKIPPING Frame Skipping From 0 to 9 From 1 to 5 Curriculum Learning for Recurrent VOS - 69 of 144 time
FRAME SKIPPING Frame Skipping From 0 to 9 From 1 to 5 Curriculum Learning for Recurrent VOS - 70 of 144 time
FRAME SKIPPING Frame Skipping From 0 to 9 From 1 to 5 Curriculum Learning for Recurrent VOS - 71 of 144 time ...
FRAME SKIPPING Frame Skipping From 0 to 9 From 1 to 5 All training All training Curriculum Learning for Recurrent VOS - 72 of 144
FRAME SKIPPING Frame Skipping From 0 to 9 From 1 to 5 All training All training Curriculum Learning for Recurrent VOS - 73 of 144
FRAME SKIPPING Frame Skipping From 0 to 9 From 1 to 5 All training All training Curriculum Learning for Recurrent VOS - 74 of 144
FRAME SKIPPING Frame Skipping From 0 to 9 From 1 to 5 All training First half training All training First half training Curriculum Learning for Recurrent VOS - 75 of 144
FRAME SKIPPING Frame Skipping From 0 to 9 From 1 to 5 All training First half training All training First half training Curriculum Learning for Recurrent VOS - 76 of 144
FRAME SKIPPING Frame Skipping From 0 to 9 From 1 to 5 All training First half training All training First half training Curriculum Learning for Recurrent VOS - 77 of 144
FRAME SKIPPING Curriculum Learning for Recurrent VOS - 78 of 144 RESULTS ON THE FRAME SKIPPING APPLIED DURING ALL TRAINING
FRAME SKIPPING Curriculum Learning for Recurrent VOS - 79 of 144 RESULTS ON THE FRAME SKIPPING APPLIED ONLY WITH GROUND-TRUTH
FRAME SKIPPING Curriculum Learning for Recurrent VOS - 80 of 144 OVERVIEW
FRAME SKIPPING Curriculum Learning for Recurrent VOS - 81 of 144 OVERVIEW
TEMPORAL AND SPATIAL RECURRENCES
TEMPORAL AND SPATIAL RECURRENCES Curriculum Learning for Recurrent VOS - 83 of 144 KITTI-MOTS is a crowded dataset:
TEMPORAL AND SPATIAL RECURRENCES Curriculum Learning for Recurrent VOS - 84 of 144 time (frame sequence) space(objectsequence)
TEMPORAL AND SPATIAL RECURRENCES Curriculum Learning for Recurrent VOS - 85 of 144 time (frame sequence) TEMPORAL RECURRENCE
TEMPORAL AND SPATIAL RECURRENCES Curriculum Learning for Recurrent VOS - 86 of 144 space(objectsequence) SPATIAL RECURRENCE
TEMPORAL AND SPATIAL RECURRENCES Proposed curriculum: Curriculum Learning for Recurrent VOS - 87 of 144
TEMPORAL AND SPATIAL RECURRENCES Temporal and Spatial Recurrence Only temporal during the first half of training Curriculum Learning for Recurrent VOS - 88 of 144
TEMPORAL AND SPATIAL RECURRENCES Temporal and Spatial Recurrence Spatio-temporal during all training Only temporal during the first half of training Curriculum Learning for Recurrent VOS - 89 of 144
TEMPORAL AND SPATIAL RECURRENCES Temporal and Spatial Recurrence Spatio-temporal during all training Only temporal during all training Only temporal during the first half of training Curriculum Learning for Recurrent VOS - 90 of 144
TEMPORAL AND SPATIAL RECURRENCES Temporal and Spatial Recurrence Spatio-temporal during all training Only temporal during all training Only temporal during the first half of training Only temporal during the second half of training Curriculum Learning for Recurrent VOS - 91 of 144
TEMPORAL AND SPATIAL RECURRENCES Curriculum Learning for Recurrent VOS - 92 of 144
TEMPORAL AND SPATIAL RECURRENCES Curriculum Learning for Recurrent VOS - 93 of 144
TEMPORAL AND SPATIAL RECURRENCES Curriculum Learning for Recurrent VOS - 94 of 144 Ground-truth
TEMPORAL AND SPATIAL RECURRENCES Curriculum Learning for Recurrent VOS - 95 of 144 Only Spatio-Temporal Ground-truth
TEMPORAL AND SPATIAL RECURRENCES Curriculum Learning for Recurrent VOS - 96 of 144 Only Spatio-Temporal Only Temporal Ground-truth
TEMPORAL AND SPATIAL RECURRENCES Curriculum Learning for Recurrent VOS - 97 of 144 Only Spatio-Temporal Only Temporal Only Temporal first half Ground-truth
TEMPORAL AND SPATIAL RECURRENCES Curriculum Learning for Recurrent VOS - 98 of 144 Only Spatio-Temporal Only Temporal Only Temporal first half Only Temporal second half Ground-truth
TEMPORAL AND SPATIAL RECURRENCES Curriculum Learning for Recurrent VOS - 99 of 144
LOSS PENALIZATION BY OBJECT AREA
LOSS PENALIZATION BY OBJECT AREA Curriculum Learning for Recurrent VOS - 101 of 144 KITTI-MOTS contains instances with different resolution:
LOSS PENALIZATION BY OBJECT AREA Curriculum Learning for Recurrent VOS - 102 of 144 KITTI-MOTS contains instances with different resolution:
LOSS PENALIZATION BY OBJECT AREA Curriculum Learning for Recurrent VOS - 103 of 144 KITTI-MOTS contains instances with different resolution:
LOSS PENALIZATION BY OBJECT AREA Curriculum Learning for Recurrent VOS - 104 of 144 An hypothesis is made: DIFFICULT
LOSS PENALIZATION BY OBJECT AREA Curriculum Learning for Recurrent VOS - 105 of 144 An hypothesis is made: DIFFICULT EASY
LOSS PENALIZATION BY OBJECT AREA Curriculum Learning for Recurrent VOS - 106 of 144 A curriculum is created: time
LOSS PENALIZATION BY OBJECT AREA Curriculum Learning for Recurrent VOS - 107 of 144 A curriculum is created: time
LOSS PENALIZATION BY OBJECT AREA Curriculum Learning for Recurrent VOS - 108 of 144
LOSS PENALIZATION BY OBJECT AREA Curriculum Learning for Recurrent VOS - 109 of 144 Resolution Batch Size Length clip 287x950 2 3 Resolution Batch Size Length clip 256x448 4 5
LOSS PENALIZATION BY OBJECT AREA Curriculum Learning for Recurrent VOS - 110 of 144 Resolution Batch Size Length clip 287x950 2 3 Resolution Batch Size Length clip 256x448 4 5
LAST MINUTE RESULTS
LAST MINUTE RESULTS Curriculum Learning for Recurrent VOS - 112 of 144
QUALITATIVE RESULTS
YouTube-VOS
YouTube-VOS Curriculum Learning for Recurrent VOS - 119 of 144 Ning Xu et al. “YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark”, ECCV 2018
YouTube-VOS Curriculum Learning for Recurrent VOS - 120 of 144 - Training parameters: Resolution Batch Size Length clip 256x448 4 5
YouTube-VOS Curriculum Learning for Recurrent VOS - 121 of 144 - Training parameters: - Evaluated with the official metrics of the YouTube-VOS challenge. Resolution Batch Size Length clip 256x448 4 5
YouTube-VOS Curriculum Learning for Recurrent VOS - 122 of 144 - Training parameters: - Evaluated with the official metrics of the YouTube-VOS challenge. Resolution Batch Size Length clip 256x448 4 5
YouTube-VOS Curriculum Learning for Recurrent VOS - 123 of 144 - Training parameters: - Evaluated with the official metrics of the YouTube-VOS challenge. Resolution Batch Size Length clip 256x448 4 5
YouTube-VOS Curriculum Learning for Recurrent VOS - 124 of 144 Forward Linear Inverse Linear Forward Step Inverse Linear
YouTube-VOS Curriculum Learning for Recurrent VOS - 125 of 144 Results on KITTI-MOTS Results on YouTube-VOS
YouTube-VOS Curriculum Learning for Recurrent VOS - 126 of 144 adapted Frame skipping from 0 to 3From 0 to 9
YouTube-VOS Curriculum Learning for Recurrent VOS - 127 of 144 Results on YouTube-VOSResults on KITTI-MOTS
CONCLUSIONS
CONCLUSIONS Curriculum Learning for Recurrent VOS - 129 of 144 SCHEDULE SAMPLING FRAME SKIPPING LOSS PENALIZATION BY OBJECT AREATEMPORAL AND SPATIAL RECURRENCES
CONCLUSIONS Curriculum Learning for Recurrent VOS - 130 of 144 SCHEDULE SAMPLING FRAME SKIPPING LOSS PENALIZATION BY OBJECT AREATEMPORAL AND SPATIAL RECURRENCES
CONCLUSIONS Curriculum Learning for Recurrent VOS - 131 of 144 SCHEDULE SAMPLING FRAME SKIPPING LOSS PENALIZATION BY OBJECT AREATEMPORAL AND SPATIAL RECURRENCES
CONCLUSIONS Curriculum Learning for Recurrent VOS - 132 of 144 SCHEDULE SAMPLING FRAME SKIPPING LOSS PENALIZATION BY OBJECT AREATEMPORAL AND SPATIAL RECURRENCES
CONCLUSIONS Curriculum Learning for Recurrent VOS - 133 of 144 SCHEDULE SAMPLING FRAME SKIPPING LOSS PENALIZATION BY OBJECT AREATEMPORAL AND SPATIAL RECURRENCES
CONCLUSIONS Curriculum Learning for Recurrent VOS - 134 of 144 Importance of knowing the dataset. KITTI-MOTS YouTube-VOS
CONCLUSIONS Curriculum Learning for Recurrent VOS - 135 of 144 Importance of knowing the dataset. KITTI-MOTS YouTube-VOS
CONCLUSIONS Curriculum Learning for Recurrent VOS - 136 of 144 Importance of knowing the dataset. KITTI-MOTS YouTube-VOS
FUTURE WORK Curriculum Learning for Recurrent VOS - 137 of 144
FUTURE WORK Curriculum Learning for Recurrent VOS - 138 of 144 Schedule Sampling
FUTURE WORK Curriculum Learning for Recurrent VOS - 139 of 144 Schedule Sampling Frame Skipping
FUTURE WORK Curriculum Learning for Recurrent VOS - 140 of 144 Schedule Sampling Frame Skipping Loss penalization by object area
FUTURE WORK Curriculum Learning for Recurrent VOS - 141 of 144 Schedule Sampling Frame Skipping Loss penalization by object area Other curriculums
FUTURE WORK Curriculum Learning for Recurrent VOS - 142 of 144 Schedule Sampling Frame Skipping Loss penalization by object area Other curriculums Combination of the best curriculums
WORKSHOP SUBMISSIONS Curriculum Learning for Recurrent VOS - 143 of 144 Acceptance Notification: August 3, 2020 PAD2020
Curriculum Learning for Recurrent Video Object Segmentation Maria Gonzalez Calabuig Barcelona, 24th July 2020

More Related Content

PDF
“Understand the Multimodal World with Minimal Supervision,” a Keynote Present...
byEdge AI and Vision Alliance
 
PPTX
Semantic-Aware Code Model: Elevating the Future of Software Development
byBaishakhi Ray
 
PDF
lecture_10_ruohannnnnnnnnnnnnnnnnnnnmnnn
bykhushbu maurya
 
PPTX
Grokked Transformers are Implicit Reasoners_ A Mechanistic Journey to the Edg...
bychroniclemag1
 
PDF
Grokked Transformers are Implicit Reasoners_ A Mechanistic Journey to the Edg...
bychroniclemag1
 
PDF
Deep Learning from Videos (UPC 2018)
byUniversitat Politècnica de Catalunya
 
PDF
Learning with Videos (D4L4 2017 UPC Deep Learning for Computer Vision)
byUniversitat Politècnica de Catalunya
 
PDF
Learning object dynamics in video generation
byAnant Gupta
 
“Understand the Multimodal World with Minimal Supervision,” a Keynote Present...
byEdge AI and Vision Alliance
 
Semantic-Aware Code Model: Elevating the Future of Software Development
byBaishakhi Ray
 
lecture_10_ruohannnnnnnnnnnnnnnnnnnnmnnn
bykhushbu maurya
 
Grokked Transformers are Implicit Reasoners_ A Mechanistic Journey to the Edg...
bychroniclemag1
 
Grokked Transformers are Implicit Reasoners_ A Mechanistic Journey to the Edg...
bychroniclemag1
 
Deep Learning from Videos (UPC 2018)
byUniversitat Politècnica de Catalunya
 
Learning with Videos (D4L4 2017 UPC Deep Learning for Computer Vision)
byUniversitat Politècnica de Catalunya
 
Learning object dynamics in video generation
byAnant Gupta
 

Similar to Curriculum Learning for Recurrent Video Object Segmentation

PDF
Learning Representations for Sign Language Videos - Xavier Giro - NIST TRECVI...
byUniversitat Politècnica de Catalunya
 
PDF
Self-supervised Learning from Video Sequences - Xavier Giro - UPC Barcelona 2019
byUniversitat Politècnica de Catalunya
 
PPTX
Self-Supervised Learning recent trends 1 2
byAvijitDasgupta18
 
PDF
DGDFSGegedagDZgRHFHRWSHhrbRHrwhrwsfrwhsfbvh
byVijayJ74
 
PDF
lecture_10_ruohanaaaaaaaaaaaaaaaaaaaa.pdf
byohmpareta1804
 
PDF
lecture_10_ruohanTTTTTTTTTTTTTTTTTTT.pdf
byohmpareta1804
 
PPTX
An Empirical Study of Training Self-Supervised Vision Transformers.pptx
bySangmin Woo
 
PDF
lec_11_self_supervised_learning.pdf
byAlamgirAkash3
 
PDF
Recurrent Neural Networks: RNN, LSTM, Image Captioning
byfawziarahim
 
PPTX
Introduction to continual learning
byNguyen Giang
 
PDF
Emerging Properties in Self-Supervised Vision Transformers
bySungchul Kim
 
PDF
Continual Learning: why, how, and when
byGabriele Graffieti
 
PDF
RVOS: End-to-End Recurrent Network for Video Object Segmentation (CVPR 2019)
byUniversitat Politècnica de Catalunya
 
PDF
[212]big models without big data using domain specific deep networks in data-...
byNAVER D2
 
PDF
Multimodal Residual Learning for Visual Question-Answering
byNAVER D2
 
PDF
161209 Unsupervised Learning of Video Representations using LSTMs
byJunho Cho
 
PDF
Multimodal Residual Networks for Visual QA
byJin-Hwa Kim
 
PDF
Real Time Sign Language Detection
byIRJET Journal
 
PDF
"Isolated Sign Recognition with a Siamese Neural Network of RGB and Depth Str...
byAnıl Osman Tur
 
Learning Representations for Sign Language Videos - Xavier Giro - NIST TRECVI...
byUniversitat Politècnica de Catalunya
 
Self-supervised Learning from Video Sequences - Xavier Giro - UPC Barcelona 2019
byUniversitat Politècnica de Catalunya
 
Self-Supervised Learning recent trends 1 2
byAvijitDasgupta18
 
DGDFSGegedagDZgRHFHRWSHhrbRHrwhrwsfrwhsfbvh
byVijayJ74
 
lecture_10_ruohanaaaaaaaaaaaaaaaaaaaa.pdf
byohmpareta1804
 
lecture_10_ruohanTTTTTTTTTTTTTTTTTTT.pdf
byohmpareta1804
 
An Empirical Study of Training Self-Supervised Vision Transformers.pptx
bySangmin Woo
 
lec_11_self_supervised_learning.pdf
byAlamgirAkash3
 
Recurrent Neural Networks: RNN, LSTM, Image Captioning
byfawziarahim
 
Introduction to continual learning
byNguyen Giang
 
Emerging Properties in Self-Supervised Vision Transformers
bySungchul Kim
 
Continual Learning: why, how, and when
byGabriele Graffieti
 
RVOS: End-to-End Recurrent Network for Video Object Segmentation (CVPR 2019)
byUniversitat Politècnica de Catalunya
 
[212]big models without big data using domain specific deep networks in data-...
byNAVER D2
 
Multimodal Residual Learning for Visual Question-Answering
byNAVER D2
 
161209 Unsupervised Learning of Video Representations using LSTMs
byJunho Cho
 
Multimodal Residual Networks for Visual QA
byJin-Hwa Kim
 
Real Time Sign Language Detection
byIRJET Journal
 
"Isolated Sign Recognition with a Siamese Neural Network of RGB and Depth Str...
byAnıl Osman Tur
 

More from Universitat Politècnica de Catalunya

PPTX
Generation of Synthetic Referring Expressions for Object Segmentation in Videos
byUniversitat Politècnica de Catalunya
 
PDF
The Transformer - Xavier Giró - UPC Barcelona 2021
byUniversitat Politècnica de Catalunya
 
PDF
Self-Supervised Audio-Visual Learning - Xavier Giro - UPC TelecomBCN Barcelon...
byUniversitat Politècnica de Catalunya
 
PDF
Deep Self-supervised Learning for All - Xavier Giro - X-Europe 2020
byUniversitat Politècnica de Catalunya
 
PDF
Attention for Deep Learning - Xavier Giro - UPC TelecomBCN Barcelona 2020
byUniversitat Politècnica de Catalunya
 
PDF
Deep Generative Learning for All
byUniversitat Politècnica de Catalunya
 
PPTX
Discovery and Learning of Navigation Goals from Pixels in Minecraft
byUniversitat Politècnica de Catalunya
 
PDF
Open challenges in sign language translation and production
byUniversitat Politècnica de Catalunya
 
PDF
Learn2Sign : Sign language recognition and translation using human keypoint e...
byUniversitat Politècnica de Catalunya
 
PDF
Towards Sign Language Translation & Production | Xavier Giro-i-Nieto
byUniversitat Politècnica de Catalunya
 
PDF
Image Segmentation with Deep Learning - Xavier Giro & Carles Ventura - ISSonD...
byUniversitat Politècnica de Catalunya
 
PDF
Q-Learning with a Neural Network - Xavier Giró - UPC Barcelona 2020
byUniversitat Politècnica de Catalunya
 
PDF
Deep Generative Learning for All - The Gen AI Hype (Spring 2024)
byUniversitat Politècnica de Catalunya
 
PDF
Deep Learning Representations for All - Xavier Giro-i-Nieto - IRI Barcelona 2020
byUniversitat Politècnica de Catalunya
 
PDF
Intepretability / Explainable AI for Deep Neural Networks
byUniversitat Politècnica de Catalunya
 
PDF
Generative Adversarial Networks GAN - Xavier Giro - UPC TelecomBCN Barcelona ...
byUniversitat Politècnica de Catalunya
 
PDF
The Transformer in Vision | Xavier Giro | Master in Computer Vision Barcelona...
byUniversitat Politècnica de Catalunya
 
PDF
Convolutional Neural Networks - Xavier Giro - UPC TelecomBCN Barcelona 2020
byUniversitat Politècnica de Catalunya
 
PDF
Language and Vision with Deep Learning - Xavier Giró - ACM ICMR 2020 (Tutorial)
byUniversitat Politècnica de Catalunya
 
PDF
Transcription-Enriched Joint Embeddings for Spoken Descriptions of Images and...
byUniversitat Politècnica de Catalunya
 
Generation of Synthetic Referring Expressions for Object Segmentation in Videos
byUniversitat Politècnica de Catalunya
 
The Transformer - Xavier Giró - UPC Barcelona 2021
byUniversitat Politècnica de Catalunya
 
Self-Supervised Audio-Visual Learning - Xavier Giro - UPC TelecomBCN Barcelon...
byUniversitat Politècnica de Catalunya
 
Deep Self-supervised Learning for All - Xavier Giro - X-Europe 2020
byUniversitat Politècnica de Catalunya
 
Attention for Deep Learning - Xavier Giro - UPC TelecomBCN Barcelona 2020
byUniversitat Politècnica de Catalunya
 
Deep Generative Learning for All
byUniversitat Politècnica de Catalunya
 
Discovery and Learning of Navigation Goals from Pixels in Minecraft
byUniversitat Politècnica de Catalunya
 
Open challenges in sign language translation and production
byUniversitat Politècnica de Catalunya
 
Learn2Sign : Sign language recognition and translation using human keypoint e...
byUniversitat Politècnica de Catalunya
 
Towards Sign Language Translation & Production | Xavier Giro-i-Nieto
byUniversitat Politècnica de Catalunya
 
Image Segmentation with Deep Learning - Xavier Giro & Carles Ventura - ISSonD...
byUniversitat Politècnica de Catalunya
 
Q-Learning with a Neural Network - Xavier Giró - UPC Barcelona 2020
byUniversitat Politècnica de Catalunya
 
Deep Generative Learning for All - The Gen AI Hype (Spring 2024)
byUniversitat Politècnica de Catalunya
 
Deep Learning Representations for All - Xavier Giro-i-Nieto - IRI Barcelona 2020
byUniversitat Politècnica de Catalunya
 
Intepretability / Explainable AI for Deep Neural Networks
byUniversitat Politècnica de Catalunya
 
Generative Adversarial Networks GAN - Xavier Giro - UPC TelecomBCN Barcelona ...
byUniversitat Politècnica de Catalunya
 
The Transformer in Vision | Xavier Giro | Master in Computer Vision Barcelona...
byUniversitat Politècnica de Catalunya
 
Convolutional Neural Networks - Xavier Giro - UPC TelecomBCN Barcelona 2020
byUniversitat Politècnica de Catalunya
 
Language and Vision with Deep Learning - Xavier Giró - ACM ICMR 2020 (Tutorial)
byUniversitat Politècnica de Catalunya
 
Transcription-Enriched Joint Embeddings for Spoken Descriptions of Images and...
byUniversitat Politècnica de Catalunya
 

Recently uploaded

PDF
Steven Imrisek | Quantitative UX Research Portfolio: Two Digital Health Case ...
bysteven180178
 
PPTX
Summary of 2025 Change Capability Survey Results.pptx
bymelanie841238
 
PDF
Starting with SPSS.pdf spss software by ibm
byMuditMathur39
 
PPTX
Data_Analysis_Plan-corrected-Biostatistics.pptx
byFahmida Swati
 
PPTX
Engineering Project Proposal by Slidesgo.pptx
bythub2306144
 
PDF
OLAP (Online Analytical Processing) is a technology used for quickly analyzin...
bykibreabtsigabu16
 
PDF
System Center 2025 Migration: Preparing for a Smooth Transition
byNiCE IT Management Solutions GmbH
 
PPT
atomic structure2.ppt qwgdwgdwidgqwuidg wdhwgdwgwydg qwgdwydgwydg87
byleonciaamolato001
 
PDF
The Hidden Risks in Linux Power Monitoring and How to Fix Them
byNiCE IT Management Solutions GmbH
 
PDF
Calculating qualified non-mutagenic impurity levels Harmonization.pdf
byFbioTeixeiradaSilva
 
PPTX
MC25104 - Data structures and algorithms using python Python_OOP_Theory_and_P...
byjanaki raman
 
PPTX
Anjna_DFT_PPTeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeee.pptx
byBENGUERBAYacine
 
PPTX
spam detacting system.pptx for mca students
bybibhutipanda012
 
PDF
Google Gemini Learning Guide - Generating Text, Vision Model, and Embeddings ...
byRohit Garg
 
PPT
fgfdgdgdgdfgerst4t4tqwweqe3eawdsfsdsdsdd
bymohamedtarekabdelrou
 
PPT
Java Swing in java object oriented progaming.ppt
byCarlos701746
 
PPT
Data Structures in java programing and ICT.ppt
byCarlos701746
 
PPTX
Chinese economy in the era a modern world
byAnwaar Ahmed
 
PPTX
Approach to Intra-Hepatic Cholestasis.pptx
byA Vijula Anbazhagan
 
PPT
Acids and alkalis ppt.ppt SVfhasvas jhsvdhsvduisa
byleonciaamolato001
 
Steven Imrisek | Quantitative UX Research Portfolio: Two Digital Health Case ...
bysteven180178
 
Summary of 2025 Change Capability Survey Results.pptx
bymelanie841238
 
Starting with SPSS.pdf spss software by ibm
byMuditMathur39
 
Data_Analysis_Plan-corrected-Biostatistics.pptx
byFahmida Swati
 
Engineering Project Proposal by Slidesgo.pptx
bythub2306144
 
OLAP (Online Analytical Processing) is a technology used for quickly analyzin...
bykibreabtsigabu16
 
System Center 2025 Migration: Preparing for a Smooth Transition
byNiCE IT Management Solutions GmbH
 
atomic structure2.ppt qwgdwgdwidgqwuidg wdhwgdwgwydg qwgdwydgwydg87
byleonciaamolato001
 
The Hidden Risks in Linux Power Monitoring and How to Fix Them
byNiCE IT Management Solutions GmbH
 
Calculating qualified non-mutagenic impurity levels Harmonization.pdf
byFbioTeixeiradaSilva
 
MC25104 - Data structures and algorithms using python Python_OOP_Theory_and_P...
byjanaki raman
 
Anjna_DFT_PPTeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeee.pptx
byBENGUERBAYacine
 
spam detacting system.pptx for mca students
bybibhutipanda012
 
Google Gemini Learning Guide - Generating Text, Vision Model, and Embeddings ...
byRohit Garg
 
fgfdgdgdgdfgerst4t4tqwweqe3eawdsfsdsdsdd
bymohamedtarekabdelrou
 
Java Swing in java object oriented progaming.ppt
byCarlos701746
 
Data Structures in java programing and ICT.ppt
byCarlos701746
 
Chinese economy in the era a modern world
byAnwaar Ahmed
 
Approach to Intra-Hepatic Cholestasis.pptx
byA Vijula Anbazhagan
 
Acids and alkalis ppt.ppt SVfhasvas jhsvdhsvduisa
byleonciaamolato001
 

Curriculum Learning for Recurrent Video Object Segmentation