SlideShare une entreprise Scribd logo

Learning to compare: relation network for few shot learning

•Télécharger en tant que PPTX, PDF•
•
S
Simon John

PPT for paper reading. Titlt: Learning to compare: relation network for few shot learning

Formation
1  sur  16
孙奕帆 Few-shot learning Meta-learning
Few-shot learning Must train a classifier to recognize new classes given few examples from each. Train set (Relatively large) Test set Support set (Relatively small)
Few-shot learning Must train a classifier to recognize new classes given few examples from each. Train set (Relatively large) Test set Support set (Relatively small) Disjoint label space Same label space Same label space
Relation network--classifying by comparison Relation network (RN) compares support images and query images and makes classification according to the returned “relation scores” Test set Support set (Relatively small) Query images Support images Relation scores Discussion: Converting classification task into retrieval task?
Relation network--classifying by comparison Relation network (RN) learn to compare with meta-learning: to mimic the comparison procedure on the training set and learn the model. Query set Sample set Query images Support images Relation scores Train set In each episode
Relation network--classifying by comparison Relation network (RN) learn to compare with meta-learning: to mimic the comparison procedure on the training set and learn the model. Query set Sample set Query images Support images Relation scores Train set In each episode C-way K-shot
Relation network--structure
Relation network--structure Embedding module relation module 𝑟𝑖,𝑗 is bounded between (0,1) by sigmoid function
Relation network--structure Embedding module relation module Optimization target:
Relation network--structure A detail for K-shot: K embedded features are pooled by pixel-wise sum operation
Relation network--structure Detailed structure Extension to 0-shot learning: different embedding module for sample and query images Semantic vector images
Experiments
Why does RN work? Both deep feature embedding and deep distance metric are learnable. (the concatenation operation is in relatively bottom layers ) When training a siamese network or a triplet network, we apply metric constraint on a specified feature and then use the Euclidean distance (or other fixed metric) for metric for inference.
Why does RN work? 2D data space
Why does RN work? The feature embeddings are difficult to separate. The relation module pair representations are linearly separable
Why does RN work? My guess 1)Feature concatenation operation in very early stage (bottom layers) 2)K sample images to mimic the K-shot 3) Converting classification to ”comparison”, which is a semi-parameter model approach.

Recommandé

OPTIMIZATION AS A MODEL FOR FEW-SHOT LEARNING
OPTIMIZATION AS A MODEL FOR FEW-SHOT LEARNING OPTIMIZATION AS A MODEL FOR FEW-SHOT LEARNING
OPTIMIZATION AS A MODEL FOR FEW-SHOT LEARNINGMLReview
 
Few shot learning/ one shot learning/ machine learning
Few shot learning/ one shot learning/ machine learningFew shot learning/ one shot learning/ machine learning
Few shot learning/ one shot learning/ machine learningﺁﺻﻒ ﻋﻠﯽ ﻣﯿﺮ
 
Optimization as a model for few shot learning
Optimization as a model for few shot learningOptimization as a model for few shot learning
Optimization as a model for few shot learningKaty Lee
 
Meta learning with memory augmented neural network
Meta learning with memory augmented neural networkMeta learning with memory augmented neural network
Meta learning with memory augmented neural networkKaty Lee
 
One shot learning
One shot learningOne shot learning
One shot learningVuong Ho Ngoc
 
Siamese networks
Siamese networksSiamese networks
Siamese networksNicholas McClure
 
Neural netorksmatching
Neural netorksmatchingNeural netorksmatching
Neural netorksmatchingMasa Kato
 
Artificial Intelligence, Machine Learning and Deep Learning
Artificial Intelligence, Machine Learning and Deep LearningArtificial Intelligence, Machine Learning and Deep Learning
Artificial Intelligence, Machine Learning and Deep LearningSujit Pal
 

Recommandé

OPTIMIZATION AS A MODEL FOR FEW-SHOT LEARNING
OPTIMIZATION AS A MODEL FOR FEW-SHOT LEARNING OPTIMIZATION AS A MODEL FOR FEW-SHOT LEARNING
OPTIMIZATION AS A MODEL FOR FEW-SHOT LEARNINGMLReview
 
Few shot learning/ one shot learning/ machine learning
Few shot learning/ one shot learning/ machine learningFew shot learning/ one shot learning/ machine learning
Few shot learning/ one shot learning/ machine learningﺁﺻﻒ ﻋﻠﯽ ﻣﯿﺮ
 
Optimization as a model for few shot learning
Optimization as a model for few shot learningOptimization as a model for few shot learning
Optimization as a model for few shot learningKaty Lee
 
Meta learning with memory augmented neural network
Meta learning with memory augmented neural networkMeta learning with memory augmented neural network
Meta learning with memory augmented neural networkKaty Lee
 
One shot learning
One shot learningOne shot learning
One shot learningVuong Ho Ngoc
 
Siamese networks
Siamese networksSiamese networks
Siamese networksNicholas McClure
 
Neural netorksmatching
Neural netorksmatchingNeural netorksmatching
Neural netorksmatchingMasa Kato
 
Artificial Intelligence, Machine Learning and Deep Learning
Artificial Intelligence, Machine Learning and Deep LearningArtificial Intelligence, Machine Learning and Deep Learning
Artificial Intelligence, Machine Learning and Deep LearningSujit Pal
 
Machine Learning: Introduction to Neural Networks
Machine Learning: Introduction to Neural NetworksMachine Learning: Introduction to Neural Networks
Machine Learning: Introduction to Neural NetworksFrancesco Collova'
 
Zero shot-learning: paper presentation
Zero shot-learning: paper presentationZero shot-learning: paper presentation
Zero shot-learning: paper presentationJérémie Kalfon
 
Deep Learning via Semi-Supervised Embedding （第 7 回 Deep Learning 勉強会資料; 大澤）
Deep Learning via Semi-Supervised Embedding （第 7 回 Deep Learning 勉強会資料; 大澤）Deep Learning via Semi-Supervised Embedding （第 7 回 Deep Learning 勉強会資料; 大澤）
Deep Learning via Semi-Supervised Embedding （第 7 回 Deep Learning 勉強会資料; 大澤）Ohsawa Goodfellow
 
Convolutional Neural Networks: Part 1
Convolutional Neural Networks: Part 1Convolutional Neural Networks: Part 1
Convolutional Neural Networks: Part 1ananth
 
15857 cse422 unsupervised-learning
15857 cse422 unsupervised-learning15857 cse422 unsupervised-learning
15857 cse422 unsupervised-learningAnil Yadav
 
ICML 2017 Meta network
ICML 2017 Meta networkICML 2017 Meta network
ICML 2017 Meta networkKaty Lee
 
MetaPerturb: Transferable Regularizer for Heterogeneous Tasks and Architectures
MetaPerturb: Transferable Regularizer for Heterogeneous Tasks and ArchitecturesMetaPerturb: Transferable Regularizer for Heterogeneous Tasks and Architectures
MetaPerturb: Transferable Regularizer for Heterogeneous Tasks and ArchitecturesMLAI2
 
TensorFlow in 3 sentences
TensorFlow in 3 sentencesTensorFlow in 3 sentences
TensorFlow in 3 sentencesBarbara Fusinska
 
Task Adaptive Neural Network Search with Meta-Contrastive Learning
Task Adaptive Neural Network Search with Meta-Contrastive LearningTask Adaptive Neural Network Search with Meta-Contrastive Learning
Task Adaptive Neural Network Search with Meta-Contrastive LearningMLAI2
 
Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distrib...
Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distrib...Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distrib...
Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distrib...MLAI2
 
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
 
Slides ppt
Slides pptSlides ppt
Slides pptbutest
 
Image classification with Deep Neural Networks
Image classification with Deep Neural NetworksImage classification with Deep Neural Networks
Image classification with Deep Neural NetworksYogendra Tamang
 
Deep Learning and Tensorflow Implementation(딥러닝, 텐서플로우, 파이썬, CNN)_Myungyon Ki...
Deep Learning and Tensorflow Implementation(딥러닝, 텐서플로우, 파이썬, CNN)_Myungyon Ki...Deep Learning and Tensorflow Implementation(딥러닝, 텐서플로우, 파이썬, CNN)_Myungyon Ki...
Deep Learning and Tensorflow Implementation(딥러닝, 텐서플로우, 파이썬, CNN)_Myungyon Ki...Myungyon Kim
 
Introduction to Convolutional Neural Networks
Introduction to Convolutional Neural NetworksIntroduction to Convolutional Neural Networks
Introduction to Convolutional Neural NetworksHannes Hapke
 
PR-258: From ImageNet to Image Classification: Contextualizing Progress on Be...
PR-258: From ImageNet to Image Classification: Contextualizing Progress on Be...PR-258: From ImageNet to Image Classification: Contextualizing Progress on Be...
PR-258: From ImageNet to Image Classification: Contextualizing Progress on Be...Jinwon Lee
 
Overview of TensorFlow For Natural Language Processing
Overview of TensorFlow For Natural Language ProcessingOverview of TensorFlow For Natural Language Processing
Overview of TensorFlow For Natural Language Processingananth
 
Using Deep Learning to Find Similar Dresses
Using Deep Learning to Find Similar DressesUsing Deep Learning to Find Similar Dresses
Using Deep Learning to Find Similar DressesHJ van Veen
 
Semi-supervised Learning
Semi-supervised LearningSemi-supervised Learning
Semi-supervised Learningbutest
 
Introduction of Machine learning and Deep Learning
Introduction of Machine learning and Deep LearningIntroduction of Machine learning and Deep Learning
Introduction of Machine learning and Deep LearningMadhu Sanjeevi (Mady)
 
Introduction to Machine Learning with SciKit-Learn
Introduction to Machine Learning with SciKit-LearnIntroduction to Machine Learning with SciKit-Learn
Introduction to Machine Learning with SciKit-LearnBenjamin Bengfort
 
PaperReview_ “Few-shot Graph Classification with Contrastive Loss and Meta-cl...
PaperReview_ “Few-shot Graph Classification with Contrastive Loss and Meta-cl...PaperReview_ “Few-shot Graph Classification with Contrastive Loss and Meta-cl...
PaperReview_ “Few-shot Graph Classification with Contrastive Loss and Meta-cl...AkankshaRawat53
 

Contenu connexe

Tendances

Machine Learning: Introduction to Neural Networks
Machine Learning: Introduction to Neural NetworksMachine Learning: Introduction to Neural Networks
Machine Learning: Introduction to Neural NetworksFrancesco Collova'
 
Zero shot-learning: paper presentation
Zero shot-learning: paper presentationZero shot-learning: paper presentation
Zero shot-learning: paper presentationJérémie Kalfon
 
Deep Learning via Semi-Supervised Embedding （第 7 回 Deep Learning 勉強会資料; 大澤）
Deep Learning via Semi-Supervised Embedding （第 7 回 Deep Learning 勉強会資料; 大澤）Deep Learning via Semi-Supervised Embedding （第 7 回 Deep Learning 勉強会資料; 大澤）
Deep Learning via Semi-Supervised Embedding （第 7 回 Deep Learning 勉強会資料; 大澤）Ohsawa Goodfellow
 
Convolutional Neural Networks: Part 1
Convolutional Neural Networks: Part 1Convolutional Neural Networks: Part 1
Convolutional Neural Networks: Part 1ananth
 
15857 cse422 unsupervised-learning
15857 cse422 unsupervised-learning15857 cse422 unsupervised-learning
15857 cse422 unsupervised-learningAnil Yadav
 
ICML 2017 Meta network
ICML 2017 Meta networkICML 2017 Meta network
ICML 2017 Meta networkKaty Lee
 
MetaPerturb: Transferable Regularizer for Heterogeneous Tasks and Architectures
MetaPerturb: Transferable Regularizer for Heterogeneous Tasks and ArchitecturesMetaPerturb: Transferable Regularizer for Heterogeneous Tasks and Architectures
MetaPerturb: Transferable Regularizer for Heterogeneous Tasks and ArchitecturesMLAI2
 
Task Adaptive Neural Network Search with Meta-Contrastive Learning
Task Adaptive Neural Network Search with Meta-Contrastive LearningTask Adaptive Neural Network Search with Meta-Contrastive Learning
Task Adaptive Neural Network Search with Meta-Contrastive LearningMLAI2
 
Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distrib...
Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distrib...Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distrib...
Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distrib...MLAI2
 
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
 
Slides ppt
Slides pptSlides ppt
Slides pptbutest
 
Image classification with Deep Neural Networks
Image classification with Deep Neural NetworksImage classification with Deep Neural Networks
Image classification with Deep Neural NetworksYogendra Tamang
 
Deep Learning and Tensorflow Implementation(딥러닝, 텐서플로우, 파이썬, CNN)_Myungyon Ki...
Deep Learning and Tensorflow Implementation(딥러닝, 텐서플로우, 파이썬, CNN)_Myungyon Ki...Deep Learning and Tensorflow Implementation(딥러닝, 텐서플로우, 파이썬, CNN)_Myungyon Ki...
Deep Learning and Tensorflow Implementation(딥러닝, 텐서플로우, 파이썬, CNN)_Myungyon Ki...Myungyon Kim
 
Introduction to Convolutional Neural Networks
Introduction to Convolutional Neural NetworksIntroduction to Convolutional Neural Networks
Introduction to Convolutional Neural NetworksHannes Hapke
 
PR-258: From ImageNet to Image Classification: Contextualizing Progress on Be...
PR-258: From ImageNet to Image Classification: Contextualizing Progress on Be...PR-258: From ImageNet to Image Classification: Contextualizing Progress on Be...
PR-258: From ImageNet to Image Classification: Contextualizing Progress on Be...Jinwon Lee
 
Overview of TensorFlow For Natural Language Processing
Overview of TensorFlow For Natural Language ProcessingOverview of TensorFlow For Natural Language Processing
Overview of TensorFlow For Natural Language Processingananth
 
Using Deep Learning to Find Similar Dresses
Using Deep Learning to Find Similar DressesUsing Deep Learning to Find Similar Dresses
Using Deep Learning to Find Similar DressesHJ van Veen
 
Semi-supervised Learning
Semi-supervised LearningSemi-supervised Learning
Semi-supervised Learningbutest
 
Introduction of Machine learning and Deep Learning
Introduction of Machine learning and Deep LearningIntroduction of Machine learning and Deep Learning
Introduction of Machine learning and Deep LearningMadhu Sanjeevi (Mady)
 

Tendances (20)

Machine Learning: Introduction to Neural Networks
Machine Learning: Introduction to Neural NetworksMachine Learning: Introduction to Neural Networks
Machine Learning: Introduction to Neural Networks
 
Zero shot-learning: paper presentation
Zero shot-learning: paper presentationZero shot-learning: paper presentation
Zero shot-learning: paper presentation
 
Deep Learning via Semi-Supervised Embedding （第 7 回 Deep Learning 勉強会資料; 大澤）
Deep Learning via Semi-Supervised Embedding （第 7 回 Deep Learning 勉強会資料; 大澤）Deep Learning via Semi-Supervised Embedding （第 7 回 Deep Learning 勉強会資料; 大澤）
Deep Learning via Semi-Supervised Embedding （第 7 回 Deep Learning 勉強会資料; 大澤）
 
Convolutional Neural Networks: Part 1
Convolutional Neural Networks: Part 1Convolutional Neural Networks: Part 1
Convolutional Neural Networks: Part 1
 
15857 cse422 unsupervised-learning
15857 cse422 unsupervised-learning15857 cse422 unsupervised-learning
15857 cse422 unsupervised-learning
 
ICML 2017 Meta network
ICML 2017 Meta networkICML 2017 Meta network
ICML 2017 Meta network
 
MetaPerturb: Transferable Regularizer for Heterogeneous Tasks and Architectures
MetaPerturb: Transferable Regularizer for Heterogeneous Tasks and ArchitecturesMetaPerturb: Transferable Regularizer for Heterogeneous Tasks and Architectures
MetaPerturb: Transferable Regularizer for Heterogeneous Tasks and Architectures
 
TensorFlow in 3 sentences
TensorFlow in 3 sentencesTensorFlow in 3 sentences
TensorFlow in 3 sentences
 
Task Adaptive Neural Network Search with Meta-Contrastive Learning
Task Adaptive Neural Network Search with Meta-Contrastive LearningTask Adaptive Neural Network Search with Meta-Contrastive Learning
Task Adaptive Neural Network Search with Meta-Contrastive Learning
 
Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distrib...
Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distrib...Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distrib...
Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distrib...
 
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 ...
 
Slides ppt
Slides pptSlides ppt
Slides ppt
 
Image classification with Deep Neural Networks
Image classification with Deep Neural NetworksImage classification with Deep Neural Networks
Image classification with Deep Neural Networks
 
Deep Learning and Tensorflow Implementation(딥러닝, 텐서플로우, 파이썬, CNN)_Myungyon Ki...
Deep Learning and Tensorflow Implementation(딥러닝, 텐서플로우, 파이썬, CNN)_Myungyon Ki...Deep Learning and Tensorflow Implementation(딥러닝, 텐서플로우, 파이썬, CNN)_Myungyon Ki...
Deep Learning and Tensorflow Implementation(딥러닝, 텐서플로우, 파이썬, CNN)_Myungyon Ki...
 
Introduction to Convolutional Neural Networks
Introduction to Convolutional Neural NetworksIntroduction to Convolutional Neural Networks
Introduction to Convolutional Neural Networks
 
PR-258: From ImageNet to Image Classification: Contextualizing Progress on Be...
PR-258: From ImageNet to Image Classification: Contextualizing Progress on Be...PR-258: From ImageNet to Image Classification: Contextualizing Progress on Be...
PR-258: From ImageNet to Image Classification: Contextualizing Progress on Be...
 
Overview of TensorFlow For Natural Language Processing
Overview of TensorFlow For Natural Language ProcessingOverview of TensorFlow For Natural Language Processing
Overview of TensorFlow For Natural Language Processing
 
Using Deep Learning to Find Similar Dresses
Using Deep Learning to Find Similar DressesUsing Deep Learning to Find Similar Dresses
Using Deep Learning to Find Similar Dresses
 
Semi-supervised Learning
Semi-supervised LearningSemi-supervised Learning
Semi-supervised Learning
 
Introduction of Machine learning and Deep Learning
Introduction of Machine learning and Deep LearningIntroduction of Machine learning and Deep Learning
Introduction of Machine learning and Deep Learning
 

Similaire à Learning to compare: relation network for few shot learning

Introduction to Machine Learning with SciKit-Learn
Introduction to Machine Learning with SciKit-LearnIntroduction to Machine Learning with SciKit-Learn
Introduction to Machine Learning with SciKit-LearnBenjamin Bengfort
 
PaperReview_ “Few-shot Graph Classification with Contrastive Loss and Meta-cl...
PaperReview_ “Few-shot Graph Classification with Contrastive Loss and Meta-cl...PaperReview_ “Few-shot Graph Classification with Contrastive Loss and Meta-cl...
PaperReview_ “Few-shot Graph Classification with Contrastive Loss and Meta-cl...AkankshaRawat53
 
Review : Prototype Mixture Models for Few-shot Semantic Segmentation
Review : Prototype Mixture Models for Few-shot Semantic SegmentationReview : Prototype Mixture Models for Few-shot Semantic Segmentation
Review : Prototype Mixture Models for Few-shot Semantic SegmentationDongmin Choi
 
Presentation
PresentationPresentation
Presentationbutest
 
Semantic Image Retrieval Using Relevance Feedback
Semantic Image Retrieval Using Relevance Feedback Semantic Image Retrieval Using Relevance Feedback
Semantic Image Retrieval Using Relevance Feedback dannyijwest
 
Unsupervised/Self-supervvised visual object tracking
Unsupervised/Self-supervvised visual object trackingUnsupervised/Self-supervvised visual object tracking
Unsupervised/Self-supervvised visual object trackingYu Huang
 
acmsigtalkshare-121023190142-phpapp01.pptx
acmsigtalkshare-121023190142-phpapp01.pptxacmsigtalkshare-121023190142-phpapp01.pptx
acmsigtalkshare-121023190142-phpapp01.pptxdongchangim30
 
A Low Rank Mechanism to Detect and Achieve Partially Completed Image Tags
A Low Rank Mechanism to Detect and Achieve Partially Completed Image TagsA Low Rank Mechanism to Detect and Achieve Partially Completed Image Tags
A Low Rank Mechanism to Detect and Achieve Partially Completed Image TagsIRJET Journal
 
Spine net learning scale permuted backbone for recognition and localization
Spine net learning scale permuted backbone for recognition and localizationSpine net learning scale permuted backbone for recognition and localization
Spine net learning scale permuted backbone for recognition and localizationDevansh16
 
Learning a Joint Embedding Representation for Image Search using Self-supervi...
Learning a Joint Embedding Representation for Image Search using Self-supervi...Learning a Joint Embedding Representation for Image Search using Self-supervi...
Learning a Joint Embedding Representation for Image Search using Self-supervi...Sujit Pal
 
AWS re:Invent 2016: Using MXNet for Recommendation Modeling at Scale (MAC306)
AWS re:Invent 2016: Using MXNet for Recommendation Modeling at Scale (MAC306)AWS re:Invent 2016: Using MXNet for Recommendation Modeling at Scale (MAC306)
AWS re:Invent 2016: Using MXNet for Recommendation Modeling at Scale (MAC306)Amazon Web Services
 
powerpoint
powerpointpowerpoint
powerpointbutest
 
LEARNING TO RANK IMAGE TAGS WITH LIMITED TRAINING EXAMPLES - IEEE PROJECTS I...
LEARNING TO RANK IMAGE TAGS WITH LIMITED TRAINING EXAMPLES - IEEE PROJECTS I...LEARNING TO RANK IMAGE TAGS WITH LIMITED TRAINING EXAMPLES - IEEE PROJECTS I...
LEARNING TO RANK IMAGE TAGS WITH LIMITED TRAINING EXAMPLES - IEEE PROJECTS I...Nexgen Technology
 
LEARNING TO RANK IMAGE TAGS WITH LIMITED TRAINING EXAMPLES
LEARNING TO RANK IMAGE TAGS WITH LIMITED TRAINING EXAMPLESLEARNING TO RANK IMAGE TAGS WITH LIMITED TRAINING EXAMPLES
LEARNING TO RANK IMAGE TAGS WITH LIMITED TRAINING EXAMPLESnexgentechnology
 
Learning to rank image tags with limited
Learning to rank image tags with limitedLearning to rank image tags with limited
Learning to rank image tags with limitednexgentech15
 
An attribute assisted reranking model
An attribute assisted reranking modelAn attribute assisted reranking model
An attribute assisted reranking modeljpstudcorner
 
IEEE 2015 Matlab Projects
IEEE 2015 Matlab ProjectsIEEE 2015 Matlab Projects
IEEE 2015 Matlab ProjectsVijay Karan
 
Learning from similarity and information extraction from structured documents...
Learning from similarity and information extraction from structured documents...Learning from similarity and information extraction from structured documents...
Learning from similarity and information extraction from structured documents...Infrrd
 
Learning to rank image tags with limited training examples
Learning to rank image tags with limited training examplesLearning to rank image tags with limited training examples
Learning to rank image tags with limited training examplesCloudTechnologies
 

Similaire à Learning to compare: relation network for few shot learning (20)

Introduction to Machine Learning with SciKit-Learn
Introduction to Machine Learning with SciKit-LearnIntroduction to Machine Learning with SciKit-Learn
Introduction to Machine Learning with SciKit-Learn
 
PaperReview_ “Few-shot Graph Classification with Contrastive Loss and Meta-cl...
PaperReview_ “Few-shot Graph Classification with Contrastive Loss and Meta-cl...PaperReview_ “Few-shot Graph Classification with Contrastive Loss and Meta-cl...
PaperReview_ “Few-shot Graph Classification with Contrastive Loss and Meta-cl...
 
Review : Prototype Mixture Models for Few-shot Semantic Segmentation
Review : Prototype Mixture Models for Few-shot Semantic SegmentationReview : Prototype Mixture Models for Few-shot Semantic Segmentation
Review : Prototype Mixture Models for Few-shot Semantic Segmentation
 
Presentation
PresentationPresentation
Presentation
 
Semantic Image Retrieval Using Relevance Feedback
Semantic Image Retrieval Using Relevance Feedback Semantic Image Retrieval Using Relevance Feedback
Semantic Image Retrieval Using Relevance Feedback
 
Unsupervised/Self-supervvised visual object tracking
Unsupervised/Self-supervvised visual object trackingUnsupervised/Self-supervvised visual object tracking
Unsupervised/Self-supervvised visual object tracking
 
acmsigtalkshare-121023190142-phpapp01.pptx
acmsigtalkshare-121023190142-phpapp01.pptxacmsigtalkshare-121023190142-phpapp01.pptx
acmsigtalkshare-121023190142-phpapp01.pptx
 
A Low Rank Mechanism to Detect and Achieve Partially Completed Image Tags
A Low Rank Mechanism to Detect and Achieve Partially Completed Image TagsA Low Rank Mechanism to Detect and Achieve Partially Completed Image Tags
A Low Rank Mechanism to Detect and Achieve Partially Completed Image Tags
 
Spine net learning scale permuted backbone for recognition and localization
Spine net learning scale permuted backbone for recognition and localizationSpine net learning scale permuted backbone for recognition and localization
Spine net learning scale permuted backbone for recognition and localization
 
Learning a Joint Embedding Representation for Image Search using Self-supervi...
Learning a Joint Embedding Representation for Image Search using Self-supervi...Learning a Joint Embedding Representation for Image Search using Self-supervi...
Learning a Joint Embedding Representation for Image Search using Self-supervi...
 
AWS re:Invent 2016: Using MXNet for Recommendation Modeling at Scale (MAC306)
AWS re:Invent 2016: Using MXNet for Recommendation Modeling at Scale (MAC306)AWS re:Invent 2016: Using MXNet for Recommendation Modeling at Scale (MAC306)
AWS re:Invent 2016: Using MXNet for Recommendation Modeling at Scale (MAC306)
 
powerpoint
powerpointpowerpoint
powerpoint
 
LEARNING TO RANK IMAGE TAGS WITH LIMITED TRAINING EXAMPLES - IEEE PROJECTS I...
LEARNING TO RANK IMAGE TAGS WITH LIMITED TRAINING EXAMPLES - IEEE PROJECTS I...LEARNING TO RANK IMAGE TAGS WITH LIMITED TRAINING EXAMPLES - IEEE PROJECTS I...
LEARNING TO RANK IMAGE TAGS WITH LIMITED TRAINING EXAMPLES - IEEE PROJECTS I...
 
LEARNING TO RANK IMAGE TAGS WITH LIMITED TRAINING EXAMPLES
LEARNING TO RANK IMAGE TAGS WITH LIMITED TRAINING EXAMPLESLEARNING TO RANK IMAGE TAGS WITH LIMITED TRAINING EXAMPLES
LEARNING TO RANK IMAGE TAGS WITH LIMITED TRAINING EXAMPLES
 
Learning to rank image tags with limited
Learning to rank image tags with limitedLearning to rank image tags with limited
Learning to rank image tags with limited
 
An attribute assisted reranking model
An attribute assisted reranking modelAn attribute assisted reranking model
An attribute assisted reranking model
 
Summary2 (1)
Summary2 (1)Summary2 (1)
Summary2 (1)
 
IEEE 2015 Matlab Projects
IEEE 2015 Matlab ProjectsIEEE 2015 Matlab Projects
IEEE 2015 Matlab Projects
 
Learning from similarity and information extraction from structured documents...
Learning from similarity and information extraction from structured documents...Learning from similarity and information extraction from structured documents...
Learning from similarity and information extraction from structured documents...
 
Learning to rank image tags with limited training examples
Learning to rank image tags with limited training examplesLearning to rank image tags with limited training examples
Learning to rank image tags with limited training examples
 

Dernier

Unit-IV; Professional Sales Representative (PSR).pptx
Unit-IV; Professional Sales Representative (PSR).pptxUnit-IV; Professional Sales Representative (PSR).pptx
Unit-IV; Professional Sales Representative (PSR).pptxVishalSingh1417
 
1029-Danh muc Sach Giao Khoa khoi 6.pdf
1029-Danh muc Sach Giao Khoa khoi 6.pdf1029-Danh muc Sach Giao Khoa khoi 6.pdf
1029-Danh muc Sach Giao Khoa khoi 6.pdfQucHHunhnh
 
Accessible design: Minimum effort, maximum impact
Accessible design: Minimum effort, maximum impactAccessible design: Minimum effort, maximum impact
Accessible design: Minimum effort, maximum impactdawncurless
 
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptxSOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptxiammrhaywood
 
Web & Social Media Analytics Previous Year Question Paper.pdf
Web & Social Media Analytics Previous Year Question Paper.pdfWeb & Social Media Analytics Previous Year Question Paper.pdf
Web & Social Media Analytics Previous Year Question Paper.pdfJayanti Pande
 
Measures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and ModeMeasures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and ModeThiyagu K
 
Application orientated numerical on hev.ppt
Application orientated numerical on hev.pptApplication orientated numerical on hev.ppt
Application orientated numerical on hev.pptRamjanShidvankar
 
psychiatric nursing HISTORY COLLECTION .docx
psychiatric nursing HISTORY COLLECTION .docxpsychiatric nursing HISTORY COLLECTION .docx
psychiatric nursing HISTORY COLLECTION .docxPoojaSen20
 
APM Welcome, APM North West Network Conference, Synergies Across Sectors
APM Welcome, APM North West Network Conference, Synergies Across SectorsAPM Welcome, APM North West Network Conference, Synergies Across Sectors
APM Welcome, APM North West Network Conference, Synergies Across SectorsAssociation for Project Management
 
PROCESS RECORDING FORMAT.docx
PROCESS RECORDING FORMAT.docxPROCESS RECORDING FORMAT.docx
PROCESS RECORDING FORMAT.docxPoojaSen20
 
ICT Role in 21st Century Education & its Challenges.pptx
ICT Role in 21st Century Education & its Challenges.pptxICT Role in 21st Century Education & its Challenges.pptx
ICT Role in 21st Century Education & its Challenges.pptxAreebaZafar22
 
Measures of Dispersion and Variability: Range, QD, AD and SD
Measures of Dispersion and Variability: Range, QD, AD and SDMeasures of Dispersion and Variability: Range, QD, AD and SD
Measures of Dispersion and Variability: Range, QD, AD and SDThiyagu K
 
Activity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfActivity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfciinovamais
 
microwave assisted reaction. General introduction
microwave assisted reaction. General introductionmicrowave assisted reaction. General introduction
microwave assisted reaction. General introductionMaksud Ahmed
 
Introduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The BasicsIntroduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The BasicsTechSoup
 
Unit-V; Pricing (Pharma Marketing Management).pptx
Unit-V; Pricing (Pharma Marketing Management).pptxUnit-V; Pricing (Pharma Marketing Management).pptx
Unit-V; Pricing (Pharma Marketing Management).pptxVishalSingh1417
 

Dernier (20)

Unit-IV; Professional Sales Representative (PSR).pptx
Unit-IV; Professional Sales Representative (PSR).pptxUnit-IV; Professional Sales Representative (PSR).pptx
Unit-IV; Professional Sales Representative (PSR).pptx
 
1029-Danh muc Sach Giao Khoa khoi 6.pdf
1029-Danh muc Sach Giao Khoa khoi 6.pdf1029-Danh muc Sach Giao Khoa khoi 6.pdf
1029-Danh muc Sach Giao Khoa khoi 6.pdf
 
Accessible design: Minimum effort, maximum impact
Accessible design: Minimum effort, maximum impactAccessible design: Minimum effort, maximum impact
Accessible design: Minimum effort, maximum impact
 
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptxSOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
SOCIAL AND HISTORICAL CONTEXT - LFTVD.pptx
 
Web & Social Media Analytics Previous Year Question Paper.pdf
Web & Social Media Analytics Previous Year Question Paper.pdfWeb & Social Media Analytics Previous Year Question Paper.pdf
Web & Social Media Analytics Previous Year Question Paper.pdf
 
Measures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and ModeMeasures of Central Tendency: Mean, Median and Mode
Measures of Central Tendency: Mean, Median and Mode
 
Mattingly "AI & Prompt Design: The Basics of Prompt Design"
Mattingly "AI & Prompt Design: The Basics of Prompt Design"Mattingly "AI & Prompt Design: The Basics of Prompt Design"
Mattingly "AI & Prompt Design: The Basics of Prompt Design"
 
Application orientated numerical on hev.ppt
Application orientated numerical on hev.pptApplication orientated numerical on hev.ppt
Application orientated numerical on hev.ppt
 
psychiatric nursing HISTORY COLLECTION .docx
psychiatric nursing HISTORY COLLECTION .docxpsychiatric nursing HISTORY COLLECTION .docx
psychiatric nursing HISTORY COLLECTION .docx
 
Código Creativo y Arte de Software | Unidad 1
Código Creativo y Arte de Software | Unidad 1Código Creativo y Arte de Software | Unidad 1
Código Creativo y Arte de Software | Unidad 1
 
APM Welcome, APM North West Network Conference, Synergies Across Sectors
APM Welcome, APM North West Network Conference, Synergies Across SectorsAPM Welcome, APM North West Network Conference, Synergies Across Sectors
APM Welcome, APM North West Network Conference, Synergies Across Sectors
 
PROCESS RECORDING FORMAT.docx
PROCESS RECORDING FORMAT.docxPROCESS RECORDING FORMAT.docx
PROCESS RECORDING FORMAT.docx
 
ICT Role in 21st Century Education & its Challenges.pptx
ICT Role in 21st Century Education & its Challenges.pptxICT Role in 21st Century Education & its Challenges.pptx
ICT Role in 21st Century Education & its Challenges.pptx
 
Measures of Dispersion and Variability: Range, QD, AD and SD
Measures of Dispersion and Variability: Range, QD, AD and SDMeasures of Dispersion and Variability: Range, QD, AD and SD
Measures of Dispersion and Variability: Range, QD, AD and SD
 
Activity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfActivity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdf
 
microwave assisted reaction. General introduction
microwave assisted reaction. General introductionmicrowave assisted reaction. General introduction
microwave assisted reaction. General introduction
 
Introduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The BasicsIntroduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The Basics
 
INDIA QUIZ 2024 RLAC DELHI UNIVERSITY.pptx
INDIA QUIZ 2024 RLAC DELHI UNIVERSITY.pptxINDIA QUIZ 2024 RLAC DELHI UNIVERSITY.pptx
INDIA QUIZ 2024 RLAC DELHI UNIVERSITY.pptx
 
Unit-V; Pricing (Pharma Marketing Management).pptx
Unit-V; Pricing (Pharma Marketing Management).pptxUnit-V; Pricing (Pharma Marketing Management).pptx
Unit-V; Pricing (Pharma Marketing Management).pptx
 
Advance Mobile Application Development class 07
Advance Mobile Application Development class 07Advance Mobile Application Development class 07
Advance Mobile Application Development class 07
 

Learning to compare: relation network for few shot learning

  • 2. Few-shot learning Must train a classifier to recognize new classes given few examples from each. Train set (Relatively large) Test set Support set (Relatively small)
  • 3. Few-shot learning Must train a classifier to recognize new classes given few examples from each. Train set (Relatively large) Test set Support set (Relatively small) Disjoint label space Same label space Same label space
  • 4. Relation network--classifying by comparison Relation network (RN) compares support images and query images and makes classification according to the returned “relation scores” Test set Support set (Relatively small) Query images Support images Relation scores Discussion: Converting classification task into retrieval task?
  • 5. Relation network--classifying by comparison Relation network (RN) learn to compare with meta-learning: to mimic the comparison procedure on the training set and learn the model. Query set Sample set Query images Support images Relation scores Train set In each episode
  • 6. Relation network--classifying by comparison Relation network (RN) learn to compare with meta-learning: to mimic the comparison procedure on the training set and learn the model. Query set Sample set Query images Support images Relation scores Train set In each episode C-way K-shot
  • 8. Relation network--structure Embedding module relation module 𝑟𝑖,𝑗 is bounded between (0,1) by sigmoid function
  • 10. Relation network--structure A detail for K-shot: K embedded features are pooled by pixel-wise sum operation
  • 11. Relation network--structure Detailed structure Extension to 0-shot learning: different embedding module for sample and query images Semantic vector images
  • 13. Why does RN work? Both deep feature embedding and deep distance metric are learnable. (the concatenation operation is in relatively bottom layers ) When training a siamese network or a triplet network, we apply metric constraint on a specified feature and then use the Euclidean distance (or other fixed metric) for metric for inference.
  • 14. Why does RN work? 2D data space
  • 15. Why does RN work? The feature embeddings are difficult to separate. The relation module pair representations are linearly separable
  • 16. Why does RN work? My guess 1)Feature concatenation operation in very early stage (bottom layers) 2)K sample images to mimic the K-shot 3) Converting classification to ”comparison”, which is a semi-parameter model approach.