unsupervised deep learning by neighbourhood discovery
play

Unsupervised Deep Learning by Neighbourhood Discovery ICML-2019 - PowerPoint PPT Presentation

Aug 18, 2022 •314 likes •535 views

Unsupervised Deep Learning by Neighbourhood Discovery ICML-2019 Jiabo Huang 1 Qi Dong 1 Shaogang Gong 1 Xiatian Zhu 2 1 Queen Mary University of London 2 Vision Semantic Ltd. Related Works & Motivation Related Works Clustering

  1. Unsupervised Deep Learning by Neighbourhood Discovery ICML-2019 Jiabo Huang 1 Qi Dong 1 Shaogang Gong 1 Xiatian Zhu 2 1 Queen Mary University of London 2 Vision Semantic Ltd.

  2. Related Works & Motivation Ø Related Works • Clustering Analysis: Caron et al. , ECCV, 2018 • Sample (Instance) Specificity Learning: Wu et al ., CVPR, 2018 • Self-supervised Learning: Zhang et al. , CVPR, 2017 • Generative Model: Donahue et al ., ICLR, 2016 Ø Motivation (a) Clustering analysis: (a) 1/6

  3. Related Works & Motivation Ø Related Works • Clustering Analysis: Caron et al. , ECCV, 2018 • Sample (Instance) Specificity Learning: Wu et al ., CVPR, 2018 • Self-supervised Learning: Zhang et al. , CVPR, 2017 • Generative Model: Donahue et al ., ICLR, 2016 Ø Motivation (a) Clustering analysis: class-consistent boundaries? (a) 1/6

  4. Related Works & Motivation Ø Related Works • Clustering Analysis: Caron et al. , ECCV, 2018 • Sample (Instance) Specificity Learning: Wu et al ., CVPR, 2018 • Self-supervised Learning: Zhang et al. , CVPR, 2017 • Generative Model: Donahue et al ., ICLR, 2016 Ø Motivation (a) Clustering analysis: class-consistent boundaries? (b) Sample specificity learning: (a) (b) 1/6

  5. Related Works & Motivation Ø Related Works • Clustering Analysis: Caron et al. , ECCV, 2018 • Sample (Instance) Specificity Learning: Wu et al ., CVPR, 2018 • Self-supervised Learning: Zhang et al. , CVPR, 2017 • Generative Model: Donahue et al ., ICLR, 2016 Ø Motivation (a) Clustering analysis: class-consistent boundaries? (b) Sample specificity learning: correlation between samples? (a) (b) 1/6

  6. Related Works & Motivation Ø Related Works • Clustering Analysis: Caron et al. , ECCV, 2018 • Sample (Instance) Specificity Learning: Wu et al ., CVPR, 2018 • Self-supervised Learning: Zhang et al. , CVPR, 2017 • Generative Model: Donahue et al ., ICLR, 2016 Ø Motivation (a) Clustering analysis: class-consistent boundaries? (b) Sample specificity learning: correlation between samples? (c) Ours : Anchor Neighbourhood Discovery (a) (b) (c) 1/6

  7. Related Works & Motivation Ø Related Works • Clustering Analysis: Caron et al. , ECCV, 2018 • Sample (Instance) Specificity Learning: Wu et al ., CVPR, 2018 • Self-supervised Learning: Zhang et al. , CVPR, 2017 • Generative Model: Donahue et al ., ICLR, 2016 Ø Motivation (a) Clustering analysis: class-consistent boundaries? (b) Sample specificity learning: correlation between samples? (c) Ours : Anchor Neighbourhood Discovery Training with neighbourhoods of high-confidence only (a) (b) (c) 1/6

  8. Neighbourhood Discovery & Selection Without ground-truth labels ! -Neareset neighbourhood structure Consistent? Consistent? 2/6

  9. Neighbourhood Discovery & Selection Ø Observation: Consistency v.s. Similarity Distribution Entropy Low Entropy Similarity Consistency Sample Index High Entropy Similarity Sample Index Entropy 3/6

  10. Neighbourhood Discovery & Selection Low Entropy Similarity ! -neareset neighbours Sample Index 4/6

  11. Neighbourhood Discovery & Selection Low Entropy Class-consistent Similarity ! -neareset neighbours Neighbourhoods Sample Index Selection 4/6

  12. Neighbourhood Discovery & Selection Low Entropy Class-consistent Similarity ! -neareset neighbours Neighbourhoods Sample Index Selection 4/6

  13. Neighbourhood Discovery & Selection Low Entropy Class-consistent Similarity ! -neareset neighbours Neighbourhoods Sample Index Selection High Entropy Similarity Sample Index 4/6

  14. Training Objectives & Strategy Ø Neighbourhood Supervision Ø Curriculum Learning 1 st Round 5/6

  15. Training Objectives & Strategy Ø Neighbourhood Supervision Ø Curriculum Learning 1 st Round 2 nd Round 5/6

  16. Training Objectives & Strategy Ø Neighbourhood Supervision Ø Curriculum Learning 1 st Round 2 nd Round Last Round 5/6

  17. Experiments Ø Small scale Image Classification ( ! NN) Ø Small scale Image Classification (LC) +1.7% +6.0% -0.3% +12.5% DeepCluster ECCV’18 Accuracy Instance CVPR’18 +8.8% +6.0% AND (Ours) CIFAR10 CIFAR100 SVHN CIFAR10 CIFAR100 SVHN 6/6

  18. Experiments Ø Small scale Image Classification ( ! NN) Ø Small scale Image Classification (LC) +1.7% +6.0% -0.3% +12.5% DeepCluster ECCV’18 Accuracy Instance CVPR’18 +8.8% +6.0% AND (Ours) CIFAR10 CIFAR100 SVHN CIFAR10 CIFAR100 SVHN Ø Large scale Image Classification +5.6% Accuracy CONV1 CONV2 CONV3 CONV4 CONV5 FC ILSVRC2012 6/6

  19. Experiments Ø Small scale Image Classification ( ! NN) Ø Small scale Image Classification (LC) +1.7% +6.0% -0.3% +12.5% DeepCluster ECCV’18 Accuracy Instance CVPR’18 +8.8% +6.0% AND (Ours) CIFAR10 CIFAR100 SVHN CIFAR10 CIFAR100 SVHN Ø Fine-grained Image Classification ( ! NN) Ø Large scale Image Classification +5.3% +5.6% Accuracy Accuracy +2.8% CUB200 DOGS CONV1 CONV2 CONV3 CONV4 CONV5 FC ILSVRC2012 6/6

  20. Unsupervised Deep Learning by Neighbourhood Discovery Thank You! Code: https://github.com/Raymond-sci/AND Poster#115

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

12. Unsupervised Deep Learning CS 535 Deep Learning, Winter 2018 Fuxin Li With materials from

12. Unsupervised Deep Learning CS 535 Deep Learning, Winter 2018 Fuxin Li With materials from

12. Unsupervised Deep Learning CS 535 Deep Learning, Winter 2018 Fuxin Li With materials from Wanli Ouyang, Zsolt Kira, Lawrence Neal, Raymond Yeh, Junting Lou and Teck-Yian Lim Unsupervised Learning in General Unsupervised learning is

1.48k views • 115 slides
Unsupervised Deep Learning Tutorial - Part 2 Alex Graves MarcAurelio Ranzato

Unsupervised Deep Learning Tutorial - Part 2 Alex Graves MarcAurelio Ranzato

Unsupervised Deep Learning Tutorial - Part 2 Alex Graves MarcAurelio Ranzato gravesa@google.com ranzato@fb.com NeurIPS, 3 December 2018 Overview Practical Recipes of Unsupervised Learning Learning representations Learning to

1.16k views • 103 slides
UNSUPERVISED LEARNING, CLUSTERING UNSUPERVISED LEARNING UNSUPERVISED LEARNING Supervised

UNSUPERVISED LEARNING, CLUSTERING UNSUPERVISED LEARNING UNSUPERVISED LEARNING Supervised

UNSUPERVISED LEARNING, CLUSTERING UNSUPERVISED LEARNING UNSUPERVISED LEARNING Supervised learning: X - y pairs, f(x) function approximation Unsupervised learning: only X, no y Exploring the space of X measurements,

440 views • 14 slides
Introduction to PCA Unsupervised Learning in R Unsupervised learning Two methods of

Introduction to PCA Unsupervised Learning in R Unsupervised learning Two methods of

UNSUPERVISED LEARNING IN R Introduction to PCA Unsupervised Learning in R Unsupervised learning Two methods of clustering finding groups of homogeneous items Next up, dimensionality reduction Find structure in features

904 views • 29 slides
Unsupervised Learning and Inverse Problems with Deep Neural Networks J oan Bruna, Stphane

Unsupervised Learning and Inverse Problems with Deep Neural Networks J oan Bruna, Stphane

Unsupervised Learning and Inverse Problems with Deep Neural Networks J oan Bruna, Stphane Mallat, Ivan Dokmanic, Martin de Hoop cole Normale Suprieure www.di.ens.fr/data Deep Convolutional Networks ( x ) x ( u ) L j L 1 f M (

520 views • 47 slides
Unsupervised Subgoal Discovery Method for Learning Hierarchical Representations Jacob Rafati

Unsupervised Subgoal Discovery Method for Learning Hierarchical Representations Jacob Rafati

Unsupervised Subgoal Discovery Method for Learning Hierarchical Representations Jacob Rafati Ph.D., Electrical Engineering and Computer Science (EECS) Computational Cognitive Neuroscience Laboratory (CCNL) http://rafati.net Co-authored with David

515 views • 15 slides
Unsupervised Deep Learning Tutorial Part 1 Alex Graves MarcAurelio Ranzato NeurIPS, 3

Unsupervised Deep Learning Tutorial Part 1 Alex Graves MarcAurelio Ranzato NeurIPS, 3

Unsupervised Deep Learning Tutorial Part 1 Alex Graves MarcAurelio Ranzato NeurIPS, 3 December 2018 Part 1 Alex Graves Introduction to unsupervised learning Autoregressive models Representation learning

1.47k views • 90 slides
3D Deep Clustering a clustering framework for unsupervised learning of 3D object feature

3D Deep Clustering a clustering framework for unsupervised learning of 3D object feature

3D Deep Clustering a clustering framework for unsupervised learning of 3D object feature descriptors LAMBDA Workshop on Retrieval and Shape analysis Alexandros Georgiou M.Sc. in Algorithms, Logic and Discrete Mathematics 1/12 Problem

570 views • 53 slides
Deep-Learning: Unsupervised Generative models Deep Belief Networks Deep Stacked AutoEncoders

Deep-Learning: Unsupervised Generative models Deep Belief Networks Deep Stacked AutoEncoders

Deep-Learning: Unsupervised Generative models Deep Belief Networks Deep Stacked AutoEncoders Generative Adversarial Networks Pr. Fabien MOUTARDE Center for Robotics MINES ParisTech PSL Universit Paris Fabien.Moutarde@mines-paristech.fr

777 views • 23 slides
Accelerating drug discovery with deep neural networks literature review Tobias Sikosek Senior

Accelerating drug discovery with deep neural networks literature review Tobias Sikosek Senior

Accelerating drug discovery with deep neural networks literature review Tobias Sikosek Senior Data Scientist In Silico Unit (Heidelberg) Deep Learning Artificial intelligence Machine learning Deep learning Renewed focus on multi-layer

836 views • 50 slides
Unsupervised Video Object Segmentation for Deep Reinforcement Learning Authors: Vik Goel,

Unsupervised Video Object Segmentation for Deep Reinforcement Learning Authors: Vik Goel,

Unsupervised Video Object Segmentation for Deep Reinforcement Learning Authors: Vik Goel, Jameson Weng, Pascal Poupart Presenter: Siliang Huang Outline Problem tackled Solution proposed RL background Architecture and

857 views • 30 slides
Anomaly Detection and Categorization Using Unsupervised Deep Learning S6340 Thursday 7 th April

Anomaly Detection and Categorization Using Unsupervised Deep Learning S6340 Thursday 7 th April

Anomaly Detection and Categorization Using Unsupervised Deep Learning S6340 Thursday 7 th April 2016 GPU Technology Conference A. Stephen McGough , Noura Al Moubayed, Jonathan Cumming, Eduardo Cabrera, Peter Matthews, Toby P . Breckon, Ed

599 views • 29 slides
A Hybrid Deep Learning Approach For Chaotic Time Series Prediction Based On Unsupervised Feature

A Hybrid Deep Learning Approach For Chaotic Time Series Prediction Based On Unsupervised Feature

A Hybrid Deep Learning Approach For Chaotic Time Series Prediction Based On Unsupervised Feature Learning Norbert Ayine Agana Advisor: Abdollah Homaifar Autonomous Control & Information Technology Institute (ACIT), Departmenent of

379 views • 35 slides
Current State of Unsupervised Deep Learning William Falcon, PhD Student AGENDA AGENDA

Current State of Unsupervised Deep Learning William Falcon, PhD Student AGENDA AGENDA

Current State of Unsupervised Deep Learning William Falcon, PhD Student AGENDA AGENDA Unsupervised vs self-supervised vs supervised learning Why we don't like supervised learning Cost of supervised learning Theoretical approaches to

846 views • 46 slides
From unsupervised induction of linguistic structures from text towards applications in deep

From unsupervised induction of linguistic structures from text towards applications in deep

Alexander Panchenko From unsupervised induction of linguistic structures from text towards applications in deep learning In close collaboration with May 28, 2018 From unsupervised induction of linguistic structures to applications in deep

1.68k views • 142 slides
Unsupervised Learning and Clustering l In unsupervised learning you are given a data set with no

Unsupervised Learning and Clustering l In unsupervised learning you are given a data set with no

Unsupervised Learning and Clustering l In unsupervised learning you are given a data set with no output classifications (labels) l Clustering is an important type of unsupervised learning PCA was another type of unsupervised learning l The

858 views • 38 slides
HMIS Project Management and Annual Calendar of Expectations Ryan Burger, ICF Eric Gammons, TAC

HMIS Project Management and Annual Calendar of Expectations Ryan Burger, ICF Eric Gammons, TAC

HMIS Project Management and Annual Calendar of Expectations Ryan Burger, ICF Eric Gammons, TAC May 4 th, 2020 1 Learning Objectives Learn how to: Distinguish project management from other kinds of management Identify HMIS Lead

268 views • 25 slides
L3: CSS Basics Web Engineering 188.951 2VU SS20 Jrgen Cito L3: CSS Basics Introducing

L3: CSS Basics Web Engineering 188.951 2VU SS20 Jrgen Cito L3: CSS Basics Introducing

L3: CSS Basics Web Engineering 188.951 2VU SS20 Jrgen Cito L3: CSS Basics Introducing style and stylesheets CSS3 Selectors Box-model Units Custom Properties (CSS Variables) Learning Goals

705 views • 15 slides
Object recognition and hierarchical computation Challenges in object recognition.

Object recognition and hierarchical computation Challenges in object recognition.

Object recognition and hierarchical computation Challenges in object recognition. Fukushimas Neocognitron View-based representations of objects Poggios HMAX Forward and Feedback in visual hierarchy

473 views • 20 slides
Origin and specificity of EPN-TAP Europlanet - RI Pierre Le Sidaner B. Cecconi on behalf of

Origin and specificity of EPN-TAP Europlanet - RI Pierre Le Sidaner B. Cecconi on behalf of

Origin and specificity of EPN-TAP Europlanet - RI Pierre Le Sidaner B. Cecconi on behalf of PADC 1 Why EPN-TAP ? - PDAP was in very early version dedicated to space agency - ObsTap was in early version dedicated to Astronomy. - Need to

196 views • 15 slides
Modeling Server-side Components with UML Junichi Suzuki, Ph.D. jxs@computer.org

Modeling Server-side Components with UML Junichi Suzuki, Ph.D. jxs@computer.org

Modeling Server-side Components with UML Junichi Suzuki, Ph.D. jxs@computer.org http://www.jks.la/jxs/ School of Information and Computer Science University of California, Irvine 1 Who am I? Research fellow, UC Irvine (2000-)

519 views • 21 slides
Perkins V Comprehensive Local Needs Assessment Programs of Study Lee Chipps-Walton and Cathy

Perkins V Comprehensive Local Needs Assessment Programs of Study Lee Chipps-Walton and Cathy

Perkins V Comprehensive Local Needs Assessment Programs of Study Lee Chipps-Walton and Cathy Hammond Division of Career and Adult Education January 29, 2020 , 1 www.FLDOE.org In This Webinar We will cover Programs of Study:

597 views • 37 slides
FlowCAP2 Results: Challenges 1, 2, and 3 Nima Aghaeepour CIHR/MSFHR Strategic Training Program in

FlowCAP2 Results: Challenges 1, 2, and 3 Nima Aghaeepour CIHR/MSFHR Strategic Training Program in

FlowCAP2 Results: Challenges 1, 2, and 3 Nima Aghaeepour CIHR/MSFHR Strategic Training Program in Bioinformatics for Health Research, University of British Columbia Sep.22.2011 1 / 27 Problem Statement Binary Classification Goal: evaluate

2.49k views • 27 slides
Quite Simple Approaches for Authorship Attribution, Intrinsic Plagiarism Detection and Sexual

Quite Simple Approaches for Authorship Attribution, Intrinsic Plagiarism Detection and Sexual

Quite Simple Approaches for Authorship Attribution, Intrinsic Plagiarism Detection and Sexual Predator Identification Notebook for PAN at CLEF 2012 Anna Vartapetiance Dr. Lee Gillam Oh what a tangled web we weave, When first we practice to

307 views • 17 slides

More recommend