SlideShare a Scribd company logo
1 of 11
Download to read offline
Yamato OKAMOTO
2019/12/15
Active-Learning
(Survey)
1. Uncertainty based method
try to find the samples which are hard to learn
method title year
Using Bayesian
to estimate uncertainty
Deep bayesian active learning with image
data
ICML’17
Using non-Bayesian
to estimate uncertainty
Simple and scalable predictive uncertainty
estimation using deep ensembles
NeurIPS’17
Using dropout
to estimate uncertainty
Dropout as a Bayesian Approximation:
Representing Model Uncertainty in Deep
Learning
ICML’16
Using entropy of the softmax
to estimate uncertainty
Cost-effective active learning for deep
image classification
2017
Using ensemble
to estimate uncertainty
The power of ensembles for active learning
in image classification
CVPR’18
predict target losses of
unlabeled samples
Learning loss for active learning CVPR’19
2. Representation based method
try to find a diverse set of samples
that optimally represents the complete dataset distribution.
method title year
density-based methods
Active learning for convolutional neural
networks: A core-set approach
ICLR’2018
learns a VAE-GAN hybrid
network to select unlabeled
samples that are not well
represented in the labeled set
Variational adversarial active learning ICCV’2019
Active Learning Acquisition Function
method detail
Max Entropy
Choose pool points that maximise the predictive entropy
BALD
Choose pool points that are expected to maximise the mutual
information between predictions and model posterior
Variation Ratios
Maximise the Variation Ratios
Mean STD
Maximise mean standard deviation
APPENDIX
there exist model parameters
that produce disagreeing predictions
with high certainty
Deep bayesian active learning with image data
(ICML’17)
Bayesian deep learning:
• combine Bayesian deep learning into the active learning framework in
a practical way
Acquisition Functions and their Approximations
• Key idea is approximating traditional acquisition functions (*refer previous slide)
by the approximate distribution q∗
θ(ω)
• q∗
θ(ω) minimises the Kullback-Leibler(KL) divergence to the true model
posterior p(ω|Dtrain) given a training set Dtrain.
https://arxiv.org/pdf/1703.02910.pdf
https://arxiv.org/pdf/1901.02731.pdf
Dropout as a Bayesian Approximation: Representing
Model Uncertainty in Deep Learning (ICML’16)
Dropout approximates Bayesian:
• dropout training in deep neural networks (NNs) as
approximate Bayesian inference in deep Gaussian processes.
uncertainty can be obtained from dropout NN
• if the uncertainty envelope intersects that of other classes (such as in
the case of the middle input image), the softmax output uncertainty
can be as large as the entire space.
http://proceedings.mlr.press/v48/gal16.pdf
Minority & Most Informative Samples:
• Selected by uncertainty-based method
and added into the labeled set after active user labeling
Majority & Clearly Classified Samples:
• automatically selected and iteratively assigned pseudo-labels.
Cost-effective active learning
for deep image classification (2017)
https://arxiv.org/abs/1701.03551
softmax
output of
the CNN
Approximate Acquisition Functions
• Approximating traditional acquisition functions (*refer previous slide)
by an ensemble of N classifiers
The power of ensembles for active learning
in image classification (CVPR’18)
http://openaccess.thecvf.com/content_cvpr_2018/papers/Beluch_The_Power_of_CVPR_2018_paper.pdf
Approximate
the entropy method
by the ensemble of N classifiers
Approximate
the BALD method
by the ensemble of N classifiers
Loss prediction module:
• learn it to predict target losses of unlabeled inputs.
• Then, this module can suggest data that the target model is likely to
produce a wrong prediction.
Learning loss for active learning (CVPR’19)
https://arxiv.org/pdf/1905.03677.pdf
Active learning for convolutional neural networks: A
core-set approach (ICLR’18)
https://arxiv.org/abs/1708.00489
Core-set selection problem:
• Core-set selection problem aims to find a small subset given a large
labeled dataset such that a model learned over the small subset is
competitive over the whole dataset.
selects a batch of samples:
• choose “b” center points such that the largest distance between a data
point and its nearest center is minimized in feature space
The minimax game between the VAE and Discriminator:
Discriminator
trained to discriminate between unlabeled and labeled data.
VAE
trained to trick the adversarial network into predicting that
all data points are from the labeled pool.
 The samples that Discriminator predicts as unlabeled are informative
Variational adversarial active learning (ICCV’19)
http://openaccess.thecvf.com/content_ICCV_2019/papers/Sinha_Variational_Adversarial_Active_Learning_ICCV_2019_paper.pdf

More Related Content

What's hot

Boosting Approach to Solving Machine Learning Problems
Boosting Approach to Solving Machine Learning ProblemsBoosting Approach to Solving Machine Learning Problems
Boosting Approach to Solving Machine Learning ProblemsDr Sulaimon Afolabi
 
Ensemble learning Techniques
Ensemble learning TechniquesEnsemble learning Techniques
Ensemble learning TechniquesBabu Priyavrat
 
Bag the model with bagging
Bag the model with baggingBag the model with bagging
Bag the model with baggingChode Amarnath
 
Tracking emerges by colorizing videos
Tracking emerges by colorizing videosTracking emerges by colorizing videos
Tracking emerges by colorizing videosOh Yoojin
 
(Machine Learning) Ensemble learning
(Machine Learning) Ensemble learning (Machine Learning) Ensemble learning
(Machine Learning) Ensemble learning Omkar Rane
 
Ensemble hybrid learning technique
Ensemble hybrid learning techniqueEnsemble hybrid learning technique
Ensemble hybrid learning techniqueDishaSinha9
 
MediaEval 2016 - MLPBOON Predicting Media Interestingness System
MediaEval 2016 - MLPBOON Predicting Media Interestingness SystemMediaEval 2016 - MLPBOON Predicting Media Interestingness System
MediaEval 2016 - MLPBOON Predicting Media Interestingness Systemmultimediaeval
 
Ensemble based method for the classification of flooding event using social m...
Ensemble based method for the classification of flooding event using social m...Ensemble based method for the classification of flooding event using social m...
Ensemble based method for the classification of flooding event using social m...multimediaeval
 
Machine Learning - Ensemble Methods
Machine Learning - Ensemble MethodsMachine Learning - Ensemble Methods
Machine Learning - Ensemble MethodsAndrew Ferlitsch
 
Generating SPSS training materials in StatJR
Generating SPSS training materials in StatJRGenerating SPSS training materials in StatJR
Generating SPSS training materials in StatJRUniversity of Southampton
 

What's hot (12)

Ensemblelearning 181220105413
Ensemblelearning 181220105413Ensemblelearning 181220105413
Ensemblelearning 181220105413
 
Boosting Approach to Solving Machine Learning Problems
Boosting Approach to Solving Machine Learning ProblemsBoosting Approach to Solving Machine Learning Problems
Boosting Approach to Solving Machine Learning Problems
 
Ensemble learning Techniques
Ensemble learning TechniquesEnsemble learning Techniques
Ensemble learning Techniques
 
Bag the model with bagging
Bag the model with baggingBag the model with bagging
Bag the model with bagging
 
Tracking emerges by colorizing videos
Tracking emerges by colorizing videosTracking emerges by colorizing videos
Tracking emerges by colorizing videos
 
(Machine Learning) Ensemble learning
(Machine Learning) Ensemble learning (Machine Learning) Ensemble learning
(Machine Learning) Ensemble learning
 
Ensemble hybrid learning technique
Ensemble hybrid learning techniqueEnsemble hybrid learning technique
Ensemble hybrid learning technique
 
Ensemble learning
Ensemble learningEnsemble learning
Ensemble learning
 
MediaEval 2016 - MLPBOON Predicting Media Interestingness System
MediaEval 2016 - MLPBOON Predicting Media Interestingness SystemMediaEval 2016 - MLPBOON Predicting Media Interestingness System
MediaEval 2016 - MLPBOON Predicting Media Interestingness System
 
Ensemble based method for the classification of flooding event using social m...
Ensemble based method for the classification of flooding event using social m...Ensemble based method for the classification of flooding event using social m...
Ensemble based method for the classification of flooding event using social m...
 
Machine Learning - Ensemble Methods
Machine Learning - Ensemble MethodsMachine Learning - Ensemble Methods
Machine Learning - Ensemble Methods
 
Generating SPSS training materials in StatJR
Generating SPSS training materials in StatJRGenerating SPSS training materials in StatJR
Generating SPSS training materials in StatJR
 

Similar to (SURVEY) Active Learning

When deep learners change their mind learning dynamics for active learning
When deep learners change their mind  learning dynamics for active learningWhen deep learners change their mind  learning dynamics for active learning
When deep learners change their mind learning dynamics for active learningDevansh16
 
Deep Semi-supervised Learning methods
Deep Semi-supervised Learning methodsDeep Semi-supervised Learning methods
Deep Semi-supervised Learning methodsPrincy Joy
 
Hand Written Digit Classification
Hand Written Digit ClassificationHand Written Digit Classification
Hand Written Digit Classificationijtsrd
 
CNN FEATURES ARE ALSO GREAT AT UNSUPERVISED CLASSIFICATION
CNN FEATURES ARE ALSO GREAT AT UNSUPERVISED CLASSIFICATION CNN FEATURES ARE ALSO GREAT AT UNSUPERVISED CLASSIFICATION
CNN FEATURES ARE ALSO GREAT AT UNSUPERVISED CLASSIFICATION cscpconf
 
Types of Machine Learnig Algorithms(CART, ID3)
Types of Machine Learnig Algorithms(CART, ID3)Types of Machine Learnig Algorithms(CART, ID3)
Types of Machine Learnig Algorithms(CART, ID3)Fatimakhan325
 
Facial Emotion Detection on Children's Emotional Face
Facial Emotion Detection on Children's Emotional FaceFacial Emotion Detection on Children's Emotional Face
Facial Emotion Detection on Children's Emotional FaceTakrim Ul Islam Laskar
 
2019 cvpr paper_overview
2019 cvpr paper_overview2019 cvpr paper_overview
2019 cvpr paper_overviewLEE HOSEONG
 
2019 cvpr paper overview by Ho Seong Lee
2019 cvpr paper overview by Ho Seong Lee2019 cvpr paper overview by Ho Seong Lee
2019 cvpr paper overview by Ho Seong LeeMoazzem Hossain
 
IMAGE CLASSIFICATION USING DIFFERENT CLASSICAL APPROACHES
IMAGE CLASSIFICATION USING DIFFERENT CLASSICAL APPROACHESIMAGE CLASSIFICATION USING DIFFERENT CLASSICAL APPROACHES
IMAGE CLASSIFICATION USING DIFFERENT CLASSICAL APPROACHESVikash Kumar
 
Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detec...
Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detec...Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detec...
Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detec...IRJET Journal
 
SYNOPSIS on Parse representation and Linear SVM.
SYNOPSIS on Parse representation and Linear SVM.SYNOPSIS on Parse representation and Linear SVM.
SYNOPSIS on Parse representation and Linear SVM.bhavinecindus
 
RunPool: A Dynamic Pooling Layer for Convolution Neural Network
RunPool: A Dynamic Pooling Layer for Convolution Neural NetworkRunPool: A Dynamic Pooling Layer for Convolution Neural Network
RunPool: A Dynamic Pooling Layer for Convolution Neural NetworkPutra Wanda
 
Single Image Super Resolution using Fuzzy Deep Convolutional Networks
Single Image Super Resolution using Fuzzy Deep Convolutional NetworksSingle Image Super Resolution using Fuzzy Deep Convolutional Networks
Single Image Super Resolution using Fuzzy Deep Convolutional NetworksGreeshma M.S.R
 
Robust inference via generative classifiers for handling noisy labels
Robust inference via generative classifiers for handling noisy labelsRobust inference via generative classifiers for handling noisy labels
Robust inference via generative classifiers for handling noisy labelsKimin Lee
 
A Survey of Deep Learning Algorithms for Malware Detection
A Survey of Deep Learning Algorithms for Malware DetectionA Survey of Deep Learning Algorithms for Malware Detection
A Survey of Deep Learning Algorithms for Malware DetectionIJCSIS Research Publications
 
D1L5 Visualization (D1L2 Insight@DCU Machine Learning Workshop 2017)
D1L5 Visualization (D1L2 Insight@DCU Machine Learning Workshop 2017)D1L5 Visualization (D1L2 Insight@DCU Machine Learning Workshop 2017)
D1L5 Visualization (D1L2 Insight@DCU Machine Learning Workshop 2017)Universitat Politècnica de Catalunya
 
[Paper Review] MisGAN: Learning from Incomplete Data with Generative Adversar...
[Paper Review] MisGAN: Learning from Incomplete Data with Generative Adversar...[Paper Review] MisGAN: Learning from Incomplete Data with Generative Adversar...
[Paper Review] MisGAN: Learning from Incomplete Data with Generative Adversar...Jihoo Kim
 
Machine Learning and Real-World Applications
Machine Learning and Real-World ApplicationsMachine Learning and Real-World Applications
Machine Learning and Real-World ApplicationsMachinePulse
 
MediaEval 2015 - UNED-UV @ Retrieving Diverse Social Images Task - Poster
MediaEval 2015 - UNED-UV @ Retrieving Diverse Social Images Task - PosterMediaEval 2015 - UNED-UV @ Retrieving Diverse Social Images Task - Poster
MediaEval 2015 - UNED-UV @ Retrieving Diverse Social Images Task - Postermultimediaeval
 

Similar to (SURVEY) Active Learning (20)

When deep learners change their mind learning dynamics for active learning
When deep learners change their mind  learning dynamics for active learningWhen deep learners change their mind  learning dynamics for active learning
When deep learners change their mind learning dynamics for active learning
 
Deep Semi-supervised Learning methods
Deep Semi-supervised Learning methodsDeep Semi-supervised Learning methods
Deep Semi-supervised Learning methods
 
OOD_PPT.pptx
OOD_PPT.pptxOOD_PPT.pptx
OOD_PPT.pptx
 
Hand Written Digit Classification
Hand Written Digit ClassificationHand Written Digit Classification
Hand Written Digit Classification
 
CNN FEATURES ARE ALSO GREAT AT UNSUPERVISED CLASSIFICATION
CNN FEATURES ARE ALSO GREAT AT UNSUPERVISED CLASSIFICATION CNN FEATURES ARE ALSO GREAT AT UNSUPERVISED CLASSIFICATION
CNN FEATURES ARE ALSO GREAT AT UNSUPERVISED CLASSIFICATION
 
Types of Machine Learnig Algorithms(CART, ID3)
Types of Machine Learnig Algorithms(CART, ID3)Types of Machine Learnig Algorithms(CART, ID3)
Types of Machine Learnig Algorithms(CART, ID3)
 
Facial Emotion Detection on Children's Emotional Face
Facial Emotion Detection on Children's Emotional FaceFacial Emotion Detection on Children's Emotional Face
Facial Emotion Detection on Children's Emotional Face
 
2019 cvpr paper_overview
2019 cvpr paper_overview2019 cvpr paper_overview
2019 cvpr paper_overview
 
2019 cvpr paper overview by Ho Seong Lee
2019 cvpr paper overview by Ho Seong Lee2019 cvpr paper overview by Ho Seong Lee
2019 cvpr paper overview by Ho Seong Lee
 
IMAGE CLASSIFICATION USING DIFFERENT CLASSICAL APPROACHES
IMAGE CLASSIFICATION USING DIFFERENT CLASSICAL APPROACHESIMAGE CLASSIFICATION USING DIFFERENT CLASSICAL APPROACHES
IMAGE CLASSIFICATION USING DIFFERENT CLASSICAL APPROACHES
 
Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detec...
Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detec...Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detec...
Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detec...
 
SYNOPSIS on Parse representation and Linear SVM.
SYNOPSIS on Parse representation and Linear SVM.SYNOPSIS on Parse representation and Linear SVM.
SYNOPSIS on Parse representation and Linear SVM.
 
RunPool: A Dynamic Pooling Layer for Convolution Neural Network
RunPool: A Dynamic Pooling Layer for Convolution Neural NetworkRunPool: A Dynamic Pooling Layer for Convolution Neural Network
RunPool: A Dynamic Pooling Layer for Convolution Neural Network
 
Single Image Super Resolution using Fuzzy Deep Convolutional Networks
Single Image Super Resolution using Fuzzy Deep Convolutional NetworksSingle Image Super Resolution using Fuzzy Deep Convolutional Networks
Single Image Super Resolution using Fuzzy Deep Convolutional Networks
 
Robust inference via generative classifiers for handling noisy labels
Robust inference via generative classifiers for handling noisy labelsRobust inference via generative classifiers for handling noisy labels
Robust inference via generative classifiers for handling noisy labels
 
A Survey of Deep Learning Algorithms for Malware Detection
A Survey of Deep Learning Algorithms for Malware DetectionA Survey of Deep Learning Algorithms for Malware Detection
A Survey of Deep Learning Algorithms for Malware Detection
 
D1L5 Visualization (D1L2 Insight@DCU Machine Learning Workshop 2017)
D1L5 Visualization (D1L2 Insight@DCU Machine Learning Workshop 2017)D1L5 Visualization (D1L2 Insight@DCU Machine Learning Workshop 2017)
D1L5 Visualization (D1L2 Insight@DCU Machine Learning Workshop 2017)
 
[Paper Review] MisGAN: Learning from Incomplete Data with Generative Adversar...
[Paper Review] MisGAN: Learning from Incomplete Data with Generative Adversar...[Paper Review] MisGAN: Learning from Incomplete Data with Generative Adversar...
[Paper Review] MisGAN: Learning from Incomplete Data with Generative Adversar...
 
Machine Learning and Real-World Applications
Machine Learning and Real-World ApplicationsMachine Learning and Real-World Applications
Machine Learning and Real-World Applications
 
MediaEval 2015 - UNED-UV @ Retrieving Diverse Social Images Task - Poster
MediaEval 2015 - UNED-UV @ Retrieving Diverse Social Images Task - PosterMediaEval 2015 - UNED-UV @ Retrieving Diverse Social Images Task - Poster
MediaEval 2015 - UNED-UV @ Retrieving Diverse Social Images Task - Poster
 

More from Yamato OKAMOTO

第七回全日本コンピュータビジョン勉強会 A Multiplexed Network for End-to-End, Multilingual OCR
第七回全日本コンピュータビジョン勉強会 A Multiplexed Network for End-to-End, Multilingual OCR第七回全日本コンピュータビジョン勉強会 A Multiplexed Network for End-to-End, Multilingual OCR
第七回全日本コンピュータビジョン勉強会 A Multiplexed Network for End-to-End, Multilingual OCRYamato OKAMOTO
 
部下のマネジメントはAI開発に学べ
部下のマネジメントはAI開発に学べ部下のマネジメントはAI開発に学べ
部下のマネジメントはAI開発に学べYamato OKAMOTO
 
ICLR2020 オンライン読み会 Deep Semi-Supervised Anomaly Detection
ICLR2020 オンライン読み会 Deep Semi-Supervised Anomaly DetectionICLR2020 オンライン読み会 Deep Semi-Supervised Anomaly Detection
ICLR2020 オンライン読み会 Deep Semi-Supervised Anomaly DetectionYamato OKAMOTO
 
ICLR'2020 参加速報
ICLR'2020 参加速報ICLR'2020 参加速報
ICLR'2020 参加速報Yamato OKAMOTO
 
Domain Generalization via Model-Agnostic Learning of Semantic Features
Domain Generalization via Model-Agnostic Learning of Semantic FeaturesDomain Generalization via Model-Agnostic Learning of Semantic Features
Domain Generalization via Model-Agnostic Learning of Semantic FeaturesYamato OKAMOTO
 
[ICML2019読み会in京都] (LT)Bayesian Nonparametric Federated Learning of Neural Net...
[ICML2019読み会in京都] (LT)Bayesian Nonparametric Federated Learning of Neural Net...[ICML2019読み会in京都] (LT)Bayesian Nonparametric Federated Learning of Neural Net...
[ICML2019読み会in京都] (LT)Bayesian Nonparametric Federated Learning of Neural Net...Yamato OKAMOTO
 
[ICML2019読み会in京都] Agnostic Federated Learning
[ICML2019読み会in京都] Agnostic Federated Learning[ICML2019読み会in京都] Agnostic Federated Learning
[ICML2019読み会in京都] Agnostic Federated LearningYamato OKAMOTO
 
CVPR2019@ロングビーチ参加速報(後編 ~本会議~)
CVPR2019@ロングビーチ参加速報(後編 ~本会議~)CVPR2019@ロングビーチ参加速報(後編 ~本会議~)
CVPR2019@ロングビーチ参加速報(後編 ~本会議~)Yamato OKAMOTO
 
CVPR2019@ロングビーチ参加速報(前編~Tutorial&Workshop~)
CVPR2019@ロングビーチ参加速報(前編~Tutorial&Workshop~)CVPR2019@ロングビーチ参加速報(前編~Tutorial&Workshop~)
CVPR2019@ロングビーチ参加速報(前編~Tutorial&Workshop~)Yamato OKAMOTO
 
ICML2019@Long Beach 参加速報(5~6日目 Workshop)
ICML2019@Long Beach 参加速報(5~6日目 Workshop)ICML2019@Long Beach 参加速報(5~6日目 Workshop)
ICML2019@Long Beach 参加速報(5~6日目 Workshop)Yamato OKAMOTO
 
ICML2019@Long Beach 参加速報(最終日 Workshop)
ICML2019@Long Beach 参加速報(最終日 Workshop)ICML2019@Long Beach 参加速報(最終日 Workshop)
ICML2019@Long Beach 参加速報(最終日 Workshop)Yamato OKAMOTO
 
ICML2019@Long Beach 参加速報(4日目)
ICML2019@Long Beach 参加速報(4日目)ICML2019@Long Beach 参加速報(4日目)
ICML2019@Long Beach 参加速報(4日目)Yamato OKAMOTO
 
ICML2019@Long Beach 参加速報(3日目)
ICML2019@Long Beach 参加速報(3日目)ICML2019@Long Beach 参加速報(3日目)
ICML2019@Long Beach 参加速報(3日目)Yamato OKAMOTO
 
ICML2019@Long Beach 参加速報(2日目)
ICML2019@Long Beach 参加速報(2日目) ICML2019@Long Beach 参加速報(2日目)
ICML2019@Long Beach 参加速報(2日目) Yamato OKAMOTO
 
ICML2019@Long Beach 参加速報(1日目)
ICML2019@Long Beach 参加速報(1日目)ICML2019@Long Beach 参加速報(1日目)
ICML2019@Long Beach 参加速報(1日目)Yamato OKAMOTO
 
ICLR2019 読み会in京都 ICLRから読み取るFeature Disentangleの研究動向
ICLR2019 読み会in京都 ICLRから読み取るFeature Disentangleの研究動向ICLR2019 読み会in京都 ICLRから読み取るFeature Disentangleの研究動向
ICLR2019 読み会in京都 ICLRから読み取るFeature Disentangleの研究動向Yamato OKAMOTO
 
ICLR'19 読み会 in 京都 [LT枠] Domain Adaptationの研究動向
ICLR'19 読み会 in 京都 [LT枠] Domain Adaptationの研究動向ICLR'19 読み会 in 京都 [LT枠] Domain Adaptationの研究動向
ICLR'19 読み会 in 京都 [LT枠] Domain Adaptationの研究動向Yamato OKAMOTO
 
CVPR2019 survey Domain Adaptation on Semantic Segmentation
CVPR2019 survey Domain Adaptation on Semantic SegmentationCVPR2019 survey Domain Adaptation on Semantic Segmentation
CVPR2019 survey Domain Adaptation on Semantic SegmentationYamato OKAMOTO
 
ICLR'19 研究動向まとめ 『Domain Adaptation』『Feature Disentangle』
ICLR'19 研究動向まとめ 『Domain Adaptation』『Feature Disentangle』ICLR'19 研究動向まとめ 『Domain Adaptation』『Feature Disentangle』
ICLR'19 研究動向まとめ 『Domain Adaptation』『Feature Disentangle』Yamato OKAMOTO
 
NeurIPS2018読み会@PFN a unified feature disentangler for multi domain image tran...
NeurIPS2018読み会@PFN a unified feature disentangler for multi domain image tran...NeurIPS2018読み会@PFN a unified feature disentangler for multi domain image tran...
NeurIPS2018読み会@PFN a unified feature disentangler for multi domain image tran...Yamato OKAMOTO
 

More from Yamato OKAMOTO (20)

第七回全日本コンピュータビジョン勉強会 A Multiplexed Network for End-to-End, Multilingual OCR
第七回全日本コンピュータビジョン勉強会 A Multiplexed Network for End-to-End, Multilingual OCR第七回全日本コンピュータビジョン勉強会 A Multiplexed Network for End-to-End, Multilingual OCR
第七回全日本コンピュータビジョン勉強会 A Multiplexed Network for End-to-End, Multilingual OCR
 
部下のマネジメントはAI開発に学べ
部下のマネジメントはAI開発に学べ部下のマネジメントはAI開発に学べ
部下のマネジメントはAI開発に学べ
 
ICLR2020 オンライン読み会 Deep Semi-Supervised Anomaly Detection
ICLR2020 オンライン読み会 Deep Semi-Supervised Anomaly DetectionICLR2020 オンライン読み会 Deep Semi-Supervised Anomaly Detection
ICLR2020 オンライン読み会 Deep Semi-Supervised Anomaly Detection
 
ICLR'2020 参加速報
ICLR'2020 参加速報ICLR'2020 参加速報
ICLR'2020 参加速報
 
Domain Generalization via Model-Agnostic Learning of Semantic Features
Domain Generalization via Model-Agnostic Learning of Semantic FeaturesDomain Generalization via Model-Agnostic Learning of Semantic Features
Domain Generalization via Model-Agnostic Learning of Semantic Features
 
[ICML2019読み会in京都] (LT)Bayesian Nonparametric Federated Learning of Neural Net...
[ICML2019読み会in京都] (LT)Bayesian Nonparametric Federated Learning of Neural Net...[ICML2019読み会in京都] (LT)Bayesian Nonparametric Federated Learning of Neural Net...
[ICML2019読み会in京都] (LT)Bayesian Nonparametric Federated Learning of Neural Net...
 
[ICML2019読み会in京都] Agnostic Federated Learning
[ICML2019読み会in京都] Agnostic Federated Learning[ICML2019読み会in京都] Agnostic Federated Learning
[ICML2019読み会in京都] Agnostic Federated Learning
 
CVPR2019@ロングビーチ参加速報(後編 ~本会議~)
CVPR2019@ロングビーチ参加速報(後編 ~本会議~)CVPR2019@ロングビーチ参加速報(後編 ~本会議~)
CVPR2019@ロングビーチ参加速報(後編 ~本会議~)
 
CVPR2019@ロングビーチ参加速報(前編~Tutorial&Workshop~)
CVPR2019@ロングビーチ参加速報(前編~Tutorial&Workshop~)CVPR2019@ロングビーチ参加速報(前編~Tutorial&Workshop~)
CVPR2019@ロングビーチ参加速報(前編~Tutorial&Workshop~)
 
ICML2019@Long Beach 参加速報(5~6日目 Workshop)
ICML2019@Long Beach 参加速報(5~6日目 Workshop)ICML2019@Long Beach 参加速報(5~6日目 Workshop)
ICML2019@Long Beach 参加速報(5~6日目 Workshop)
 
ICML2019@Long Beach 参加速報(最終日 Workshop)
ICML2019@Long Beach 参加速報(最終日 Workshop)ICML2019@Long Beach 参加速報(最終日 Workshop)
ICML2019@Long Beach 参加速報(最終日 Workshop)
 
ICML2019@Long Beach 参加速報(4日目)
ICML2019@Long Beach 参加速報(4日目)ICML2019@Long Beach 参加速報(4日目)
ICML2019@Long Beach 参加速報(4日目)
 
ICML2019@Long Beach 参加速報(3日目)
ICML2019@Long Beach 参加速報(3日目)ICML2019@Long Beach 参加速報(3日目)
ICML2019@Long Beach 参加速報(3日目)
 
ICML2019@Long Beach 参加速報(2日目)
ICML2019@Long Beach 参加速報(2日目) ICML2019@Long Beach 参加速報(2日目)
ICML2019@Long Beach 参加速報(2日目)
 
ICML2019@Long Beach 参加速報(1日目)
ICML2019@Long Beach 参加速報(1日目)ICML2019@Long Beach 参加速報(1日目)
ICML2019@Long Beach 参加速報(1日目)
 
ICLR2019 読み会in京都 ICLRから読み取るFeature Disentangleの研究動向
ICLR2019 読み会in京都 ICLRから読み取るFeature Disentangleの研究動向ICLR2019 読み会in京都 ICLRから読み取るFeature Disentangleの研究動向
ICLR2019 読み会in京都 ICLRから読み取るFeature Disentangleの研究動向
 
ICLR'19 読み会 in 京都 [LT枠] Domain Adaptationの研究動向
ICLR'19 読み会 in 京都 [LT枠] Domain Adaptationの研究動向ICLR'19 読み会 in 京都 [LT枠] Domain Adaptationの研究動向
ICLR'19 読み会 in 京都 [LT枠] Domain Adaptationの研究動向
 
CVPR2019 survey Domain Adaptation on Semantic Segmentation
CVPR2019 survey Domain Adaptation on Semantic SegmentationCVPR2019 survey Domain Adaptation on Semantic Segmentation
CVPR2019 survey Domain Adaptation on Semantic Segmentation
 
ICLR'19 研究動向まとめ 『Domain Adaptation』『Feature Disentangle』
ICLR'19 研究動向まとめ 『Domain Adaptation』『Feature Disentangle』ICLR'19 研究動向まとめ 『Domain Adaptation』『Feature Disentangle』
ICLR'19 研究動向まとめ 『Domain Adaptation』『Feature Disentangle』
 
NeurIPS2018読み会@PFN a unified feature disentangler for multi domain image tran...
NeurIPS2018読み会@PFN a unified feature disentangler for multi domain image tran...NeurIPS2018読み会@PFN a unified feature disentangler for multi domain image tran...
NeurIPS2018読み会@PFN a unified feature disentangler for multi domain image tran...
 

Recently uploaded

Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Alan Dix
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slidespraypatel2
 
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersEnhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersThousandEyes
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsMemoori
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking MenDelhi Call girls
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreternaman860154
 
Azure Monitor & Application Insight to monitor Infrastructure & Application
Azure Monitor & Application Insight to monitor Infrastructure & ApplicationAzure Monitor & Application Insight to monitor Infrastructure & Application
Azure Monitor & Application Insight to monitor Infrastructure & ApplicationAndikSusilo4
 
Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Paola De la Torre
 
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...shyamraj55
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsMark Billinghurst
 
Unblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesUnblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesSinan KOZAK
 
SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024Scott Keck-Warren
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticscarlostorres15106
 
Maximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxMaximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxOnBoard
 
Pigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking MenDelhi Call girls
 
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxKatpro Technologies
 
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Patryk Bandurski
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationRadu Cotescu
 
Key Features Of Token Development (1).pptx
Key  Features Of Token  Development (1).pptxKey  Features Of Token  Development (1).pptx
Key Features Of Token Development (1).pptxLBM Solutions
 

Recently uploaded (20)

Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...
 
Slack Application Development 101 Slides
Slack Application Development 101 SlidesSlack Application Development 101 Slides
Slack Application Development 101 Slides
 
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for PartnersEnhancing Worker Digital Experience: A Hands-on Workshop for Partners
Enhancing Worker Digital Experience: A Hands-on Workshop for Partners
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial Buildings
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
 
Azure Monitor & Application Insight to monitor Infrastructure & Application
Azure Monitor & Application Insight to monitor Infrastructure & ApplicationAzure Monitor & Application Insight to monitor Infrastructure & Application
Azure Monitor & Application Insight to monitor Infrastructure & Application
 
Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101
 
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
 
Human Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR SystemsHuman Factors of XR: Using Human Factors to Design XR Systems
Human Factors of XR: Using Human Factors to Design XR Systems
 
Unblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesUnblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen Frames
 
SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024SQL Database Design For Developers at php[tek] 2024
SQL Database Design For Developers at php[tek] 2024
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
 
Maximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptxMaximizing Board Effectiveness 2024 Webinar.pptx
Maximizing Board Effectiveness 2024 Webinar.pptx
 
Pigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food ManufacturingPigging Solutions in Pet Food Manufacturing
Pigging Solutions in Pet Food Manufacturing
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men
 
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
 
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
Integration and Automation in Practice: CI/CD in Mule Integration and Automat...
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organization
 
Key Features Of Token Development (1).pptx
Key  Features Of Token  Development (1).pptxKey  Features Of Token  Development (1).pptx
Key Features Of Token Development (1).pptx
 

(SURVEY) Active Learning

  • 2. 1. Uncertainty based method try to find the samples which are hard to learn method title year Using Bayesian to estimate uncertainty Deep bayesian active learning with image data ICML’17 Using non-Bayesian to estimate uncertainty Simple and scalable predictive uncertainty estimation using deep ensembles NeurIPS’17 Using dropout to estimate uncertainty Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning ICML’16 Using entropy of the softmax to estimate uncertainty Cost-effective active learning for deep image classification 2017 Using ensemble to estimate uncertainty The power of ensembles for active learning in image classification CVPR’18 predict target losses of unlabeled samples Learning loss for active learning CVPR’19
  • 3. 2. Representation based method try to find a diverse set of samples that optimally represents the complete dataset distribution. method title year density-based methods Active learning for convolutional neural networks: A core-set approach ICLR’2018 learns a VAE-GAN hybrid network to select unlabeled samples that are not well represented in the labeled set Variational adversarial active learning ICCV’2019
  • 4. Active Learning Acquisition Function method detail Max Entropy Choose pool points that maximise the predictive entropy BALD Choose pool points that are expected to maximise the mutual information between predictions and model posterior Variation Ratios Maximise the Variation Ratios Mean STD Maximise mean standard deviation APPENDIX there exist model parameters that produce disagreeing predictions with high certainty
  • 5. Deep bayesian active learning with image data (ICML’17) Bayesian deep learning: • combine Bayesian deep learning into the active learning framework in a practical way Acquisition Functions and their Approximations • Key idea is approximating traditional acquisition functions (*refer previous slide) by the approximate distribution q∗ θ(ω) • q∗ θ(ω) minimises the Kullback-Leibler(KL) divergence to the true model posterior p(ω|Dtrain) given a training set Dtrain. https://arxiv.org/pdf/1703.02910.pdf https://arxiv.org/pdf/1901.02731.pdf
  • 6. Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning (ICML’16) Dropout approximates Bayesian: • dropout training in deep neural networks (NNs) as approximate Bayesian inference in deep Gaussian processes. uncertainty can be obtained from dropout NN • if the uncertainty envelope intersects that of other classes (such as in the case of the middle input image), the softmax output uncertainty can be as large as the entire space. http://proceedings.mlr.press/v48/gal16.pdf
  • 7. Minority & Most Informative Samples: • Selected by uncertainty-based method and added into the labeled set after active user labeling Majority & Clearly Classified Samples: • automatically selected and iteratively assigned pseudo-labels. Cost-effective active learning for deep image classification (2017) https://arxiv.org/abs/1701.03551 softmax output of the CNN
  • 8. Approximate Acquisition Functions • Approximating traditional acquisition functions (*refer previous slide) by an ensemble of N classifiers The power of ensembles for active learning in image classification (CVPR’18) http://openaccess.thecvf.com/content_cvpr_2018/papers/Beluch_The_Power_of_CVPR_2018_paper.pdf Approximate the entropy method by the ensemble of N classifiers Approximate the BALD method by the ensemble of N classifiers
  • 9. Loss prediction module: • learn it to predict target losses of unlabeled inputs. • Then, this module can suggest data that the target model is likely to produce a wrong prediction. Learning loss for active learning (CVPR’19) https://arxiv.org/pdf/1905.03677.pdf
  • 10. Active learning for convolutional neural networks: A core-set approach (ICLR’18) https://arxiv.org/abs/1708.00489 Core-set selection problem: • Core-set selection problem aims to find a small subset given a large labeled dataset such that a model learned over the small subset is competitive over the whole dataset. selects a batch of samples: • choose “b” center points such that the largest distance between a data point and its nearest center is minimized in feature space
  • 11. The minimax game between the VAE and Discriminator: Discriminator trained to discriminate between unlabeled and labeled data. VAE trained to trick the adversarial network into predicting that all data points are from the labeled pool.  The samples that Discriminator predicts as unlabeled are informative Variational adversarial active learning (ICCV’19) http://openaccess.thecvf.com/content_ICCV_2019/papers/Sinha_Variational_Adversarial_Active_Learning_ICCV_2019_paper.pdf