SlideShare a Scribd company logo
1 of 35
Download to read offline
Joint Unsupervised Learning of Deep
Representations and Image Clusters
Jianwei Yang, Devi Parikh, Dhruv Batra
[arXiv] [GitHub]
Slides by Albert Jiménez [GDoc]
Computer Vision Reading Group (23/09/2016)
1.
Introduction
The main idea
2
Learning good image representations is beneficial to image clustering
Main Idea ( 1 )
Joint Unsupervised Learning of representations and image clusters
3
Clustering provide supervisory signals for image representation
Main Idea ( 2 )
Joint Unsupervised Learning of representations and image clusters
4
Integrate both processes into a single model
● Unified triplet loss
● End-to-end training
Network Clustering
Forward - Update Clustering
Backward - Update Representation parameters
Main Idea ( 3 )
Joint Unsupervised Learning of representations and image clusters
5
2.
Clustering
Agglomerative Clustering
6
Agglomerative Clustering
What?
● At the beginning each image is a cluster
● Merge two clusters at each timestep
Affinity Measure
7
Agglomerative Clustering
Why?
● Recurrent process → Implemented in recurrent framework
● Begins with over-clustering (overcome bad initial representations)
● Clusters are merged as better representations are learned
8
Agglomerative Clustering
Affinity Measure
● Directed graph
● Affinity matrix corresponding to the edge set
Ks
→ # Nearest Neighbors
Ni
Ks
→ Ks
NN of Xi
xi,j
→ Image Representation (vertex)
ns → # Samples
a → Design Parameter = 1 9
Agglomerative Clustering
Affinity Measure
● Affinity matrix corresponding to the edge set:
● Affinity measure:
W. Zhang, X. Wang, D. Zhao, and X. Tang. Graph degree linkage: Agglomerative clustering on a directed graph.
10
3.
System Formulation
Joint Optimization
11
System Formulation
Recurrent Framework
At timestep t:
ht
→ Image cluster labels
yt
→ Output
Xt
→ Image representations
12
System Formulation
Recurrent Framework
● Unrolling strategy:
○ Complete
○ Partial
■ Split the overall T timesteps into
multiple periods
■ In each period we merge a number
of clusters and update CNN
parameters
13
Unrolling rate : control the number of timesteps
nc
s
: number of clusters at the start of p
Number of timesteps:
System Formulation
Algorithm
14
System Formulation
Objective Function
● Accumulate the losses from all the timesteps
● For y0
we take each image as a cluster, at time t we merge 2 clusters given yt-1
● In conventional agglomerative clustering
○ 2 clusters are selected by maximal Affinity measure over pairs of clusters
● In this approach
○ Consider the local structure surrounding the clusters
15
System Formulation
Objective Function
● Assuming that from yt-1
to yt
we have merged a cluster Ci
t
and its NN
Affinity between cluster Ci
and NN
Difference of affinity between cluster Ci
and NN and
affinities of Ci
with its Kc neighbor clusters
16
System Formulation
Objective Function
● Introducing this loss term:
○ Consider the local structure
surrounding the clusters
○ Allows to write the loss in terms of
triplets
17
System Formulation
Forward/Backward Pass
Network Clustering
Forward - Update Clustering
Backward - Update Representation parameters
18
System Formulation
Forward Pass
● In the forward pass of the p-th period p∈(1, ... , P), update the clusters with the
network parameters fixed
Overall loss for period p
19
● In the forward pass of the p-th period p∈(1, ... , P), we have merged a number of
clusters
● In the backward pass we aim to derive the optimal parameters to minimize the
losses generated in the forward pass.
System Formulation
Backward Pass
We accumulate the losses of p periods
20
● Loss defined on clusters
○ Need the entire dataset to estimate
○ Difficult to use batch-based optimization
● Sample based loss approximation
System Formulation
From cluster based loss to sample based
21
● Sample based loss intuition
○ Agglomerative clustering starts with each datapoint as a cluster
○ Clusters at higher level hierarchy are formed by merging lower level clusters
System Formulation
From cluster based loss to sample based
22
System Formulation
From cluster based loss to sample based
● Affinities between clusters can be expressed in terms of affinities
with datapoints
For more info check supplement of the paper
23
● Finally it has got the form of a weight triplet loss
System Formulation
From cluster based loss to sample based
is a weight whose value depends on
xi
and xj
are from the same cluster
xk
is from the Kc
nearest neighbouring clusters
24
● Given a dataset with ns
samples and nc
number of clusters, T = ns
-nc
timesteps
○ Time consuming optimization in large datasets
● Run a fast algorithm to determine initial clustering
○ Agglomerative clustering via maximum incremental path integral
System Formulation
Optimization
25
4.
Experiments
26
● They use Caffe/Torch
● Convolutional layers of 50 channels, 5x5 filters, stride = 1, padding = 0
● Pooling layers, 2x2 kernel, stride = 2
● Final size of the output feature map is 10x10
Experiments
Experimental Setup
Face datasets
27
● On top of all the CNNs they
append a IP layer (dimension
160)
● Followed by l2 norm layer
● wt-loss = weight triplet loss
Experiments
Experimental Setup
28
Experiments
Robustness Analysis
29
Experiments
Quantitative Comparison Using Image Intensities as an Input
Measure = NMI = Normalized Mutual Information
30
Experiments
Quantitative Comparison of the Other State-of-the-Art Using their Representations as Input
31
Experiments
Transfer Learning
32
Experiments
Face Verification
● Representations learn from Youtube-Face
dataset evaluated on LFW
33
5.
Conclusions
34
Conclusions
● They combine agglomerative clustering with CNNs and optimize jointly in a
recurrent framework.
● Proposal of a partial unrolling strategy to divide the timesteps into multiple
periods.
● Obtain more precise image clusters and discriminative representations.
● Able to generalize well across many datasets and tasks.
35

More Related Content

What's hot

What's hot (20)

Deep Learning for Computer Vision: Segmentation (UPC 2016)
Deep Learning for Computer Vision: Segmentation (UPC 2016)Deep Learning for Computer Vision: Segmentation (UPC 2016)
Deep Learning for Computer Vision: Segmentation (UPC 2016)
 
Deep Learning for Computer Vision: Unsupervised Learning (UPC 2016)
Deep Learning for Computer Vision: Unsupervised Learning (UPC 2016)Deep Learning for Computer Vision: Unsupervised Learning (UPC 2016)
Deep Learning for Computer Vision: Unsupervised Learning (UPC 2016)
 
Deep Learning for Computer Vision: Deep Networks (UPC 2016)
Deep Learning for Computer Vision: Deep Networks (UPC 2016)Deep Learning for Computer Vision: Deep Networks (UPC 2016)
Deep Learning for Computer Vision: Deep Networks (UPC 2016)
 
Deep Learning for Computer Vision: Attention Models (UPC 2016)
Deep Learning for Computer Vision: Attention Models (UPC 2016)Deep Learning for Computer Vision: Attention Models (UPC 2016)
Deep Learning for Computer Vision: Attention Models (UPC 2016)
 
Deep Learning for Computer Vision: Memory usage and computational considerati...
Deep Learning for Computer Vision: Memory usage and computational considerati...Deep Learning for Computer Vision: Memory usage and computational considerati...
Deep Learning for Computer Vision: Memory usage and computational considerati...
 
Optimization for Deep Networks (D2L1 2017 UPC Deep Learning for Computer Vision)
Optimization for Deep Networks (D2L1 2017 UPC Deep Learning for Computer Vision)Optimization for Deep Networks (D2L1 2017 UPC Deep Learning for Computer Vision)
Optimization for Deep Networks (D2L1 2017 UPC Deep Learning for Computer Vision)
 
Deep Learning for Computer Vision: Backward Propagation (UPC 2016)
Deep Learning for Computer Vision: Backward Propagation (UPC 2016)Deep Learning for Computer Vision: Backward Propagation (UPC 2016)
Deep Learning for Computer Vision: Backward Propagation (UPC 2016)
 
Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)
Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)
Deep Neural Networks (D1L2 Insight@DCU Machine Learning Workshop 2017)
 
Deep Learning for Computer Vision: Data Augmentation (UPC 2016)
Deep Learning for Computer Vision: Data Augmentation (UPC 2016)Deep Learning for Computer Vision: Data Augmentation (UPC 2016)
Deep Learning for Computer Vision: Data Augmentation (UPC 2016)
 
Deep Learning for Computer Vision: Visualization (UPC 2016)
Deep Learning for Computer Vision: Visualization (UPC 2016)Deep Learning for Computer Vision: Visualization (UPC 2016)
Deep Learning for Computer Vision: Visualization (UPC 2016)
 
Convolutional Neural Networks (D1L3 2017 UPC Deep Learning for Computer Vision)
Convolutional Neural Networks (D1L3 2017 UPC Deep Learning for Computer Vision)Convolutional Neural Networks (D1L3 2017 UPC Deep Learning for Computer Vision)
Convolutional Neural Networks (D1L3 2017 UPC Deep Learning for Computer Vision)
 
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)
 
Image Segmentation (D3L1 2017 UPC Deep Learning for Computer Vision)
Image Segmentation (D3L1 2017 UPC Deep Learning for Computer Vision)Image Segmentation (D3L1 2017 UPC Deep Learning for Computer Vision)
Image Segmentation (D3L1 2017 UPC Deep Learning for Computer Vision)
 
Generative Models and Adversarial Training (D3L4 2017 UPC Deep Learning for ...
Generative Models and Adversarial Training  (D3L4 2017 UPC Deep Learning for ...Generative Models and Adversarial Training  (D3L4 2017 UPC Deep Learning for ...
Generative Models and Adversarial Training (D3L4 2017 UPC Deep Learning for ...
 
Deep 3D Visual Analysis - Javier Ruiz-Hidalgo - UPC Barcelona 2017
Deep 3D Visual Analysis - Javier Ruiz-Hidalgo - UPC Barcelona 2017Deep 3D Visual Analysis - Javier Ruiz-Hidalgo - UPC Barcelona 2017
Deep 3D Visual Analysis - Javier Ruiz-Hidalgo - UPC Barcelona 2017
 
Deep Learning for Computer Vision: Transfer Learning and Domain Adaptation (U...
Deep Learning for Computer Vision: Transfer Learning and Domain Adaptation (U...Deep Learning for Computer Vision: Transfer Learning and Domain Adaptation (U...
Deep Learning for Computer Vision: Transfer Learning and Domain Adaptation (U...
 
Perceptrons (D1L2 2017 UPC Deep Learning for Computer Vision)
Perceptrons (D1L2 2017 UPC Deep Learning for Computer Vision)Perceptrons (D1L2 2017 UPC Deep Learning for Computer Vision)
Perceptrons (D1L2 2017 UPC Deep Learning for Computer Vision)
 
Multilayer Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intell...
Multilayer Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intell...Multilayer Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intell...
Multilayer Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intell...
 
Convolutional Neural Networks - Veronica Vilaplana - UPC Barcelona 2018
Convolutional Neural Networks - Veronica Vilaplana - UPC Barcelona 2018Convolutional Neural Networks - Veronica Vilaplana - UPC Barcelona 2018
Convolutional Neural Networks - Veronica Vilaplana - UPC Barcelona 2018
 
Deep Learning for Computer Vision: Generative models and adversarial training...
Deep Learning for Computer Vision: Generative models and adversarial training...Deep Learning for Computer Vision: Generative models and adversarial training...
Deep Learning for Computer Vision: Generative models and adversarial training...
 

Similar to Joint unsupervised learning of deep representations and image clusters

Convolutional Neural Networks
Convolutional Neural NetworksConvolutional Neural Networks
Convolutional Neural Networks
milad abbasi
 
CC282 Unsupervised Learning (Clustering) Lecture 7 slides for ...
CC282 Unsupervised Learning (Clustering) Lecture 7 slides for ...CC282 Unsupervised Learning (Clustering) Lecture 7 slides for ...
CC282 Unsupervised Learning (Clustering) Lecture 7 slides for ...
butest
 

Similar to Joint unsupervised learning of deep representations and image clusters (20)

DAOR - Bridging the Gap between Community and Node Representations: Graph Emb...
DAOR - Bridging the Gap between Community and Node Representations: Graph Emb...DAOR - Bridging the Gap between Community and Node Representations: Graph Emb...
DAOR - Bridging the Gap between Community and Node Representations: Graph Emb...
 
multiarmed bandit.ppt
multiarmed bandit.pptmultiarmed bandit.ppt
multiarmed bandit.ppt
 
CPQ_presentation_ICCV2021
CPQ_presentation_ICCV2021CPQ_presentation_ICCV2021
CPQ_presentation_ICCV2021
 
Waste Classification System using Convolutional Neural Networks.pptx
Waste Classification System using Convolutional Neural Networks.pptxWaste Classification System using Convolutional Neural Networks.pptx
Waste Classification System using Convolutional Neural Networks.pptx
 
Chapter 11. Cluster Analysis Advanced Methods.ppt
Chapter 11. Cluster Analysis Advanced Methods.pptChapter 11. Cluster Analysis Advanced Methods.ppt
Chapter 11. Cluster Analysis Advanced Methods.ppt
 
Cnn
CnnCnn
Cnn
 
Convolutional Neural Networks
Convolutional Neural NetworksConvolutional Neural Networks
Convolutional Neural Networks
 
VJAI Paper Reading#3-KDD2019-ClusterGCN
VJAI Paper Reading#3-KDD2019-ClusterGCNVJAI Paper Reading#3-KDD2019-ClusterGCN
VJAI Paper Reading#3-KDD2019-ClusterGCN
 
AILABS - Lecture Series - Is AI the New Electricity? Topic:- Classification a...
AILABS - Lecture Series - Is AI the New Electricity? Topic:- Classification a...AILABS - Lecture Series - Is AI the New Electricity? Topic:- Classification a...
AILABS - Lecture Series - Is AI the New Electricity? Topic:- Classification a...
 
Introduction to Applied Machine Learning
Introduction to Applied Machine LearningIntroduction to Applied Machine Learning
Introduction to Applied Machine Learning
 
Unsupervised Learning Clustering KMean and Hirarchical.pptx
Unsupervised Learning Clustering KMean and Hirarchical.pptxUnsupervised Learning Clustering KMean and Hirarchical.pptx
Unsupervised Learning Clustering KMean and Hirarchical.pptx
 
Clustering.pptx
Clustering.pptxClustering.pptx
Clustering.pptx
 
iiit delhi unsupervised pdf.pdf
iiit delhi unsupervised pdf.pdfiiit delhi unsupervised pdf.pdf
iiit delhi unsupervised pdf.pdf
 
CC282 Unsupervised Learning (Clustering) Lecture 7 slides for ...
CC282 Unsupervised Learning (Clustering) Lecture 7 slides for ...CC282 Unsupervised Learning (Clustering) Lecture 7 slides for ...
CC282 Unsupervised Learning (Clustering) Lecture 7 slides for ...
 
Learning Convolutional Neural Networks for Graphs
Learning Convolutional Neural Networks for GraphsLearning Convolutional Neural Networks for Graphs
Learning Convolutional Neural Networks for Graphs
 
K-Means, its Variants and its Applications
K-Means, its Variants and its ApplicationsK-Means, its Variants and its Applications
K-Means, its Variants and its Applications
 
k-mean-clustering.pdf
k-mean-clustering.pdfk-mean-clustering.pdf
k-mean-clustering.pdf
 
Restricting the Flow: Information Bottlenecks for Attribution
Restricting the Flow: Information Bottlenecks for AttributionRestricting the Flow: Information Bottlenecks for Attribution
Restricting the Flow: Information Bottlenecks for Attribution
 
convolutional_neural_networks in deep learning
convolutional_neural_networks in deep learningconvolutional_neural_networks in deep learning
convolutional_neural_networks in deep learning
 
deep CNN vs conventional ML
deep CNN vs conventional MLdeep CNN vs conventional ML
deep CNN vs conventional ML
 

More from Universitat Politècnica de Catalunya

Generation of Synthetic Referring Expressions for Object Segmentation in Videos
Generation of Synthetic Referring Expressions for Object Segmentation in VideosGeneration of Synthetic Referring Expressions for Object Segmentation in Videos
Generation of Synthetic Referring Expressions for Object Segmentation in Videos
Universitat Politècnica de Catalunya
 

More from Universitat Politècnica de Catalunya (20)

Deep Generative Learning for All - The Gen AI Hype (Spring 2024)
Deep Generative Learning for All - The Gen AI Hype (Spring 2024)Deep Generative Learning for All - The Gen AI Hype (Spring 2024)
Deep Generative Learning for All - The Gen AI Hype (Spring 2024)
 
Deep Generative Learning for All
Deep Generative Learning for AllDeep Generative Learning for All
Deep Generative Learning for All
 
The Transformer in Vision | Xavier Giro | Master in Computer Vision Barcelona...
The Transformer in Vision | Xavier Giro | Master in Computer Vision Barcelona...The Transformer in Vision | Xavier Giro | Master in Computer Vision Barcelona...
The Transformer in Vision | Xavier Giro | Master in Computer Vision Barcelona...
 
Towards Sign Language Translation & Production | Xavier Giro-i-Nieto
Towards Sign Language Translation & Production | Xavier Giro-i-NietoTowards Sign Language Translation & Production | Xavier Giro-i-Nieto
Towards Sign Language Translation & Production | Xavier Giro-i-Nieto
 
The Transformer - Xavier Giró - UPC Barcelona 2021
The Transformer - Xavier Giró - UPC Barcelona 2021The Transformer - Xavier Giró - UPC Barcelona 2021
The Transformer - Xavier Giró - UPC Barcelona 2021
 
Learning Representations for Sign Language Videos - Xavier Giro - NIST TRECVI...
Learning Representations for Sign Language Videos - Xavier Giro - NIST TRECVI...Learning Representations for Sign Language Videos - Xavier Giro - NIST TRECVI...
Learning Representations for Sign Language Videos - Xavier Giro - NIST TRECVI...
 
Open challenges in sign language translation and production
Open challenges in sign language translation and productionOpen challenges in sign language translation and production
Open challenges in sign language translation and production
 
Generation of Synthetic Referring Expressions for Object Segmentation in Videos
Generation of Synthetic Referring Expressions for Object Segmentation in VideosGeneration of Synthetic Referring Expressions for Object Segmentation in Videos
Generation of Synthetic Referring Expressions for Object Segmentation in Videos
 
Discovery and Learning of Navigation Goals from Pixels in Minecraft
Discovery and Learning of Navigation Goals from Pixels in MinecraftDiscovery and Learning of Navigation Goals from Pixels in Minecraft
Discovery and Learning of Navigation Goals from Pixels in Minecraft
 
Learn2Sign : Sign language recognition and translation using human keypoint e...
Learn2Sign : Sign language recognition and translation using human keypoint e...Learn2Sign : Sign language recognition and translation using human keypoint e...
Learn2Sign : Sign language recognition and translation using human keypoint e...
 
Intepretability / Explainable AI for Deep Neural Networks
Intepretability / Explainable AI for Deep Neural NetworksIntepretability / Explainable AI for Deep Neural Networks
Intepretability / Explainable AI for Deep Neural Networks
 
Convolutional Neural Networks - Xavier Giro - UPC TelecomBCN Barcelona 2020
Convolutional Neural Networks - Xavier Giro - UPC TelecomBCN Barcelona 2020Convolutional Neural Networks - Xavier Giro - UPC TelecomBCN Barcelona 2020
Convolutional Neural Networks - Xavier Giro - UPC TelecomBCN Barcelona 2020
 
Self-Supervised Audio-Visual Learning - Xavier Giro - UPC TelecomBCN Barcelon...
Self-Supervised Audio-Visual Learning - Xavier Giro - UPC TelecomBCN Barcelon...Self-Supervised Audio-Visual Learning - Xavier Giro - UPC TelecomBCN Barcelon...
Self-Supervised Audio-Visual Learning - Xavier Giro - UPC TelecomBCN Barcelon...
 
Attention for Deep Learning - Xavier Giro - UPC TelecomBCN Barcelona 2020
Attention for Deep Learning - Xavier Giro - UPC TelecomBCN Barcelona 2020Attention for Deep Learning - Xavier Giro - UPC TelecomBCN Barcelona 2020
Attention for Deep Learning - Xavier Giro - UPC TelecomBCN Barcelona 2020
 
Generative Adversarial Networks GAN - Xavier Giro - UPC TelecomBCN Barcelona ...
Generative Adversarial Networks GAN - Xavier Giro - UPC TelecomBCN Barcelona ...Generative Adversarial Networks GAN - Xavier Giro - UPC TelecomBCN Barcelona ...
Generative Adversarial Networks GAN - Xavier Giro - UPC TelecomBCN Barcelona ...
 
Q-Learning with a Neural Network - Xavier Giró - UPC Barcelona 2020
Q-Learning with a Neural Network - Xavier Giró - UPC Barcelona 2020Q-Learning with a Neural Network - Xavier Giró - UPC Barcelona 2020
Q-Learning with a Neural Network - Xavier Giró - UPC Barcelona 2020
 
Language and Vision with Deep Learning - Xavier Giró - ACM ICMR 2020 (Tutorial)
Language and Vision with Deep Learning - Xavier Giró - ACM ICMR 2020 (Tutorial)Language and Vision with Deep Learning - Xavier Giró - ACM ICMR 2020 (Tutorial)
Language and Vision with Deep Learning - Xavier Giró - ACM ICMR 2020 (Tutorial)
 
Image Segmentation with Deep Learning - Xavier Giro & Carles Ventura - ISSonD...
Image Segmentation with Deep Learning - Xavier Giro & Carles Ventura - ISSonD...Image Segmentation with Deep Learning - Xavier Giro & Carles Ventura - ISSonD...
Image Segmentation with Deep Learning - Xavier Giro & Carles Ventura - ISSonD...
 
Curriculum Learning for Recurrent Video Object Segmentation
Curriculum Learning for Recurrent Video Object SegmentationCurriculum Learning for Recurrent Video Object Segmentation
Curriculum Learning for Recurrent Video Object Segmentation
 
Deep Self-supervised Learning for All - Xavier Giro - X-Europe 2020
Deep Self-supervised Learning for All - Xavier Giro - X-Europe 2020Deep Self-supervised Learning for All - Xavier Giro - X-Europe 2020
Deep Self-supervised Learning for All - Xavier Giro - X-Europe 2020
 

Recently uploaded

Log Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptxLog Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptx
JohnnyPlasten
 
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
amitlee9823
 
Delhi 99530 vip 56974 Genuine Escort Service Call Girls in Kishangarh
Delhi 99530 vip 56974 Genuine Escort Service Call Girls in  KishangarhDelhi 99530 vip 56974 Genuine Escort Service Call Girls in  Kishangarh
Delhi 99530 vip 56974 Genuine Escort Service Call Girls in Kishangarh
9953056974 Low Rate Call Girls In Saket, Delhi NCR
 
Schema on read is obsolete. Welcome metaprogramming..pdf
Schema on read is obsolete. Welcome metaprogramming..pdfSchema on read is obsolete. Welcome metaprogramming..pdf
Schema on read is obsolete. Welcome metaprogramming..pdf
Lars Albertsson
 
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get CytotecAbortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Riyadh +966572737505 get cytotec
 

Recently uploaded (20)

Log Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptxLog Analysis using OSSEC sasoasasasas.pptx
Log Analysis using OSSEC sasoasasasas.pptx
 
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
VIP Model Call Girls Hinjewadi ( Pune ) Call ON 8005736733 Starting From 5K t...
 
Invezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signalsInvezz.com - Grow your wealth with trading signals
Invezz.com - Grow your wealth with trading signals
 
Edukaciniai dropshipping via API with DroFx
Edukaciniai dropshipping via API with DroFxEdukaciniai dropshipping via API with DroFx
Edukaciniai dropshipping via API with DroFx
 
Halmar dropshipping via API with DroFx
Halmar  dropshipping  via API with DroFxHalmar  dropshipping  via API with DroFx
Halmar dropshipping via API with DroFx
 
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% SecureCall me @ 9892124323  Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
Call me @ 9892124323 Cheap Rate Call Girls in Vashi with Real Photo 100% Secure
 
100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx100-Concepts-of-AI by Anupama Kate .pptx
100-Concepts-of-AI by Anupama Kate .pptx
 
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptxBPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
BPAC WITH UFSBI GENERAL PRESENTATION 18_05_2017-1.pptx
 
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
Chintamani Call Girls: 🍓 7737669865 🍓 High Profile Model Escorts | Bangalore ...
 
BabyOno dropshipping via API with DroFx.pptx
BabyOno dropshipping via API with DroFx.pptxBabyOno dropshipping via API with DroFx.pptx
BabyOno dropshipping via API with DroFx.pptx
 
Delhi 99530 vip 56974 Genuine Escort Service Call Girls in Kishangarh
Delhi 99530 vip 56974 Genuine Escort Service Call Girls in  KishangarhDelhi 99530 vip 56974 Genuine Escort Service Call Girls in  Kishangarh
Delhi 99530 vip 56974 Genuine Escort Service Call Girls in Kishangarh
 
Accredited-Transport-Cooperatives-Jan-2021-Web.pdf
Accredited-Transport-Cooperatives-Jan-2021-Web.pdfAccredited-Transport-Cooperatives-Jan-2021-Web.pdf
Accredited-Transport-Cooperatives-Jan-2021-Web.pdf
 
CebaBaby dropshipping via API with DroFX.pptx
CebaBaby dropshipping via API with DroFX.pptxCebaBaby dropshipping via API with DroFX.pptx
CebaBaby dropshipping via API with DroFX.pptx
 
Schema on read is obsolete. Welcome metaprogramming..pdf
Schema on read is obsolete. Welcome metaprogramming..pdfSchema on read is obsolete. Welcome metaprogramming..pdf
Schema on read is obsolete. Welcome metaprogramming..pdf
 
Mature dropshipping via API with DroFx.pptx
Mature dropshipping via API with DroFx.pptxMature dropshipping via API with DroFx.pptx
Mature dropshipping via API with DroFx.pptx
 
Data-Analysis for Chicago Crime Data 2023
Data-Analysis for Chicago Crime Data  2023Data-Analysis for Chicago Crime Data  2023
Data-Analysis for Chicago Crime Data 2023
 
Zuja dropshipping via API with DroFx.pptx
Zuja dropshipping via API with DroFx.pptxZuja dropshipping via API with DroFx.pptx
Zuja dropshipping via API with DroFx.pptx
 
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get CytotecAbortion pills in Doha Qatar (+966572737505 ! Get Cytotec
Abortion pills in Doha Qatar (+966572737505 ! Get Cytotec
 
BDSM⚡Call Girls in Mandawali Delhi >༒8448380779 Escort Service
BDSM⚡Call Girls in Mandawali Delhi >༒8448380779 Escort ServiceBDSM⚡Call Girls in Mandawali Delhi >༒8448380779 Escort Service
BDSM⚡Call Girls in Mandawali Delhi >༒8448380779 Escort Service
 
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
Best VIP Call Girls Noida Sector 39 Call Me: 8448380779
 

Joint unsupervised learning of deep representations and image clusters

  • 1. Joint Unsupervised Learning of Deep Representations and Image Clusters Jianwei Yang, Devi Parikh, Dhruv Batra [arXiv] [GitHub] Slides by Albert Jiménez [GDoc] Computer Vision Reading Group (23/09/2016)
  • 3. Learning good image representations is beneficial to image clustering Main Idea ( 1 ) Joint Unsupervised Learning of representations and image clusters 3
  • 4. Clustering provide supervisory signals for image representation Main Idea ( 2 ) Joint Unsupervised Learning of representations and image clusters 4
  • 5. Integrate both processes into a single model ● Unified triplet loss ● End-to-end training Network Clustering Forward - Update Clustering Backward - Update Representation parameters Main Idea ( 3 ) Joint Unsupervised Learning of representations and image clusters 5
  • 7. Agglomerative Clustering What? ● At the beginning each image is a cluster ● Merge two clusters at each timestep Affinity Measure 7
  • 8. Agglomerative Clustering Why? ● Recurrent process → Implemented in recurrent framework ● Begins with over-clustering (overcome bad initial representations) ● Clusters are merged as better representations are learned 8
  • 9. Agglomerative Clustering Affinity Measure ● Directed graph ● Affinity matrix corresponding to the edge set Ks → # Nearest Neighbors Ni Ks → Ks NN of Xi xi,j → Image Representation (vertex) ns → # Samples a → Design Parameter = 1 9
  • 10. Agglomerative Clustering Affinity Measure ● Affinity matrix corresponding to the edge set: ● Affinity measure: W. Zhang, X. Wang, D. Zhao, and X. Tang. Graph degree linkage: Agglomerative clustering on a directed graph. 10
  • 12. System Formulation Recurrent Framework At timestep t: ht → Image cluster labels yt → Output Xt → Image representations 12
  • 13. System Formulation Recurrent Framework ● Unrolling strategy: ○ Complete ○ Partial ■ Split the overall T timesteps into multiple periods ■ In each period we merge a number of clusters and update CNN parameters 13
  • 14. Unrolling rate : control the number of timesteps nc s : number of clusters at the start of p Number of timesteps: System Formulation Algorithm 14
  • 15. System Formulation Objective Function ● Accumulate the losses from all the timesteps ● For y0 we take each image as a cluster, at time t we merge 2 clusters given yt-1 ● In conventional agglomerative clustering ○ 2 clusters are selected by maximal Affinity measure over pairs of clusters ● In this approach ○ Consider the local structure surrounding the clusters 15
  • 16. System Formulation Objective Function ● Assuming that from yt-1 to yt we have merged a cluster Ci t and its NN Affinity between cluster Ci and NN Difference of affinity between cluster Ci and NN and affinities of Ci with its Kc neighbor clusters 16
  • 17. System Formulation Objective Function ● Introducing this loss term: ○ Consider the local structure surrounding the clusters ○ Allows to write the loss in terms of triplets 17
  • 18. System Formulation Forward/Backward Pass Network Clustering Forward - Update Clustering Backward - Update Representation parameters 18
  • 19. System Formulation Forward Pass ● In the forward pass of the p-th period p∈(1, ... , P), update the clusters with the network parameters fixed Overall loss for period p 19
  • 20. ● In the forward pass of the p-th period p∈(1, ... , P), we have merged a number of clusters ● In the backward pass we aim to derive the optimal parameters to minimize the losses generated in the forward pass. System Formulation Backward Pass We accumulate the losses of p periods 20
  • 21. ● Loss defined on clusters ○ Need the entire dataset to estimate ○ Difficult to use batch-based optimization ● Sample based loss approximation System Formulation From cluster based loss to sample based 21
  • 22. ● Sample based loss intuition ○ Agglomerative clustering starts with each datapoint as a cluster ○ Clusters at higher level hierarchy are formed by merging lower level clusters System Formulation From cluster based loss to sample based 22
  • 23. System Formulation From cluster based loss to sample based ● Affinities between clusters can be expressed in terms of affinities with datapoints For more info check supplement of the paper 23
  • 24. ● Finally it has got the form of a weight triplet loss System Formulation From cluster based loss to sample based is a weight whose value depends on xi and xj are from the same cluster xk is from the Kc nearest neighbouring clusters 24
  • 25. ● Given a dataset with ns samples and nc number of clusters, T = ns -nc timesteps ○ Time consuming optimization in large datasets ● Run a fast algorithm to determine initial clustering ○ Agglomerative clustering via maximum incremental path integral System Formulation Optimization 25
  • 27. ● They use Caffe/Torch ● Convolutional layers of 50 channels, 5x5 filters, stride = 1, padding = 0 ● Pooling layers, 2x2 kernel, stride = 2 ● Final size of the output feature map is 10x10 Experiments Experimental Setup Face datasets 27
  • 28. ● On top of all the CNNs they append a IP layer (dimension 160) ● Followed by l2 norm layer ● wt-loss = weight triplet loss Experiments Experimental Setup 28
  • 30. Experiments Quantitative Comparison Using Image Intensities as an Input Measure = NMI = Normalized Mutual Information 30
  • 31. Experiments Quantitative Comparison of the Other State-of-the-Art Using their Representations as Input 31
  • 33. Experiments Face Verification ● Representations learn from Youtube-Face dataset evaluated on LFW 33
  • 35. Conclusions ● They combine agglomerative clustering with CNNs and optimize jointly in a recurrent framework. ● Proposal of a partial unrolling strategy to divide the timesteps into multiple periods. ● Obtain more precise image clusters and discriminative representations. ● Able to generalize well across many datasets and tasks. 35