SlideShare ist ein Scribd-Unternehmen logo
1 von 28
Sparse Isotropic Hashing
Ikuro Sato, Mitsuru Ambai, Koichiro Suzuki
Denso IT Laboratory, Inc.
{isato, manbai, ksuzuki}@d-itlab.co.jp
8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 1/28
Presented at MIRU 2013, Japan.
Peer reviewed paper available at http://www.am.sanken.osaka-u.ac.jp/CVA/
• Introduction
• Proposed method
• Experiment
8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 2/36
Practical issues of large-scale image retrieval
• ex) descriptor-matching approach
millions of sums-of-product / query
?
slow
query
image
query image
DB: ~108 images
8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 3/28
Potential solution: descriptor binarization
computational time of similarity
real 512
bit
256
bit
128
bit
64
bit
32
bit
binary codes1
8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 4/28
Binarization by hash functions
1. supervised
– uses known point-to-point correspondences
• ex) Ambai et al, 2012.
2. unsupervised
– intends to preserve similarities among the original real
vectors
8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 5/28
Popular hash function
ex)
Random Proj. (Goemans et al, 1995)
Very Sparse Rand. Proj. (Li et al, 2006)
Sequential Proj. (Wang et al, 2010)
8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved.
Iterative Quantization (Gong et al, 2011)
Isotropic Hashing (Kong et al, 2012)
this work
state-of-the-art
6/28
Most related work: Isotropic Hashing (Kong et al, 2012)
1. orthonormality
2. isotropic variance
8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 7/28
Most related work: Isotropic Hashing (Kong et al, 2012)
1. orthonormality
2. isotropic variance
Robust to noise from spherically
symmetric distribution.
8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 8/28
Learning of Isotropic Hashing
• Lift and Projection (LP) algorithm
isotropic orthogonal
Gradient Flow
algorithm omitted.
intersection
8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 9/28
1) PCA:
Under-constrained problem
It’s more natural to impose additional conditions
to make the problem over-constrained.
our motivation
8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 10/28
Our contribution
8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 11/28
• Introduction
• Proposed method
• Experiment
8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 12/36
Problem setup
1. rotational matrix
2. isotropic variance
3. sparsity
8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 13/28
Condition-1: Special orthogonal group
-1
1
0
8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 14/28
Condition-2: Cost function for isotropic variance
Exact solutions exist according to the Schur-Horn Theorem (AJM1954).
8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 15/28
8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 16/28
Our optimization problem
8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 17/28
Algorithm
Sparse Isotropic Hashing (SIH)
• Repeat until convergence.
endfor
notations
simplified
8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 18/28
Illustration of the optimization process
8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 19/28
• Introduction
• Proposed method
• Experiment
8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 20/36
Dataset
etc.
* M. Ambai and I. Sato, “Fast binary coding of local descriptors based on supervised learning” (MIRU2012).
descriptor
query set
(u=1)
training set
(u=2, 3, 4)
test set
(u=5, 6)
CARD (Ambai et al, 2011)
without binarization
12896 50053 25238
# local descriptors
8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 21/28
Evaluation criterion
• Mean Average Precision (mAP)
– expected value of area under Precision-Recall curve
8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved.
precision
recall
1.0
Average
Precision
22/28
Methods compared
All methods use
8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 23/28
state-of-the-art
mAP for CARD
8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 24/28
mAP for CARD
8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 25/28
mAP for CARD
almost
on top
8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 26/28
mAP for CARD
10% drop in mAP,
20x faster coding
env.: VS2010, C program
8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 27/28
Conclusion
Isotropic Hashing (Kong et al, 2012):
highly under-constrained
8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 28/28

Weitere ähnliche Inhalte

Was ist angesagt?

200612_BioPackathon_ss
200612_BioPackathon_ss200612_BioPackathon_ss
200612_BioPackathon_ssSatoshi Kume
 
【DL輪読会】ViT + Self Supervised Learningまとめ
【DL輪読会】ViT + Self Supervised Learningまとめ【DL輪読会】ViT + Self Supervised Learningまとめ
【DL輪読会】ViT + Self Supervised LearningまとめDeep Learning JP
 
モデルアーキテクチャ観点からの高速化2019
モデルアーキテクチャ観点からの高速化2019モデルアーキテクチャ観点からの高速化2019
モデルアーキテクチャ観点からの高速化2019Yusuke Uchida
 
Deep Learning in real world @Deep Learning Tokyo
Deep Learning in real world @Deep Learning TokyoDeep Learning in real world @Deep Learning Tokyo
Deep Learning in real world @Deep Learning TokyoPreferred Networks
 
WWW 2021report public
WWW 2021report publicWWW 2021report public
WWW 2021report publicTakuma Oda
 
PLNOG 18 - Dr Marek Michalewicz - InfiniCortex: Superkomputer wielki jak świat
PLNOG 18 - Dr Marek Michalewicz - InfiniCortex: Superkomputer wielki jak światPLNOG 18 - Dr Marek Michalewicz - InfiniCortex: Superkomputer wielki jak świat
PLNOG 18 - Dr Marek Michalewicz - InfiniCortex: Superkomputer wielki jak światPROIDEA
 
從 Project Theta 到台灣人工智慧學校
從 Project Theta 到台灣人工智慧學校從 Project Theta 到台灣人工智慧學校
從 Project Theta 到台灣人工智慧學校Sheng-Wei (Kuan-Ta) Chen
 
深度學習在AOI的應用
深度學習在AOI的應用深度學習在AOI的應用
深度學習在AOI的應用CHENHuiMei
 
データサイエンティストの仕事とデータ分析コンテスト
データサイエンティストの仕事とデータ分析コンテストデータサイエンティストの仕事とデータ分析コンテスト
データサイエンティストの仕事とデータ分析コンテストKen'ichi Matsui
 
Dataset creation for Deep Learning-based Geometric Computer Vision problems
Dataset creation for Deep Learning-based Geometric Computer Vision problemsDataset creation for Deep Learning-based Geometric Computer Vision problems
Dataset creation for Deep Learning-based Geometric Computer Vision problemsPetteriTeikariPhD
 
ICC2017 UUUI sessions 6205-1
ICC2017 UUUI sessions 6205-1ICC2017 UUUI sessions 6205-1
ICC2017 UUUI sessions 6205-1UUUI ICA
 
NIPS - Deep learning @ Edge using Intel's NCS
NIPS - Deep learning @ Edge using Intel's NCSNIPS - Deep learning @ Edge using Intel's NCS
NIPS - Deep learning @ Edge using Intel's NCSgeetachauhan
 
Deep learning for FinTech
Deep learning for FinTechDeep learning for FinTech
Deep learning for FinTechgeetachauhan
 
Image verification assistant. By Polychronis Charitidis of CERTH-ITI
Image verification assistant. By Polychronis Charitidis of CERTH-ITIImage verification assistant. By Polychronis Charitidis of CERTH-ITI
Image verification assistant. By Polychronis Charitidis of CERTH-ITIWeverify
 
Capstone Design(2) 중간 발표
Capstone Design(2) 중간 발표Capstone Design(2) 중간 발표
Capstone Design(2) 중간 발표Hyunwoo Kim
 
モデル高速化百選
モデル高速化百選モデル高速化百選
モデル高速化百選Yusuke Uchida
 
Ieee gold 2010 resta
Ieee gold 2010 restaIeee gold 2010 resta
Ieee gold 2010 restagrssieee
 

Was ist angesagt? (17)

200612_BioPackathon_ss
200612_BioPackathon_ss200612_BioPackathon_ss
200612_BioPackathon_ss
 
【DL輪読会】ViT + Self Supervised Learningまとめ
【DL輪読会】ViT + Self Supervised Learningまとめ【DL輪読会】ViT + Self Supervised Learningまとめ
【DL輪読会】ViT + Self Supervised Learningまとめ
 
モデルアーキテクチャ観点からの高速化2019
モデルアーキテクチャ観点からの高速化2019モデルアーキテクチャ観点からの高速化2019
モデルアーキテクチャ観点からの高速化2019
 
Deep Learning in real world @Deep Learning Tokyo
Deep Learning in real world @Deep Learning TokyoDeep Learning in real world @Deep Learning Tokyo
Deep Learning in real world @Deep Learning Tokyo
 
WWW 2021report public
WWW 2021report publicWWW 2021report public
WWW 2021report public
 
PLNOG 18 - Dr Marek Michalewicz - InfiniCortex: Superkomputer wielki jak świat
PLNOG 18 - Dr Marek Michalewicz - InfiniCortex: Superkomputer wielki jak światPLNOG 18 - Dr Marek Michalewicz - InfiniCortex: Superkomputer wielki jak świat
PLNOG 18 - Dr Marek Michalewicz - InfiniCortex: Superkomputer wielki jak świat
 
從 Project Theta 到台灣人工智慧學校
從 Project Theta 到台灣人工智慧學校從 Project Theta 到台灣人工智慧學校
從 Project Theta 到台灣人工智慧學校
 
深度學習在AOI的應用
深度學習在AOI的應用深度學習在AOI的應用
深度學習在AOI的應用
 
データサイエンティストの仕事とデータ分析コンテスト
データサイエンティストの仕事とデータ分析コンテストデータサイエンティストの仕事とデータ分析コンテスト
データサイエンティストの仕事とデータ分析コンテスト
 
Dataset creation for Deep Learning-based Geometric Computer Vision problems
Dataset creation for Deep Learning-based Geometric Computer Vision problemsDataset creation for Deep Learning-based Geometric Computer Vision problems
Dataset creation for Deep Learning-based Geometric Computer Vision problems
 
ICC2017 UUUI sessions 6205-1
ICC2017 UUUI sessions 6205-1ICC2017 UUUI sessions 6205-1
ICC2017 UUUI sessions 6205-1
 
NIPS - Deep learning @ Edge using Intel's NCS
NIPS - Deep learning @ Edge using Intel's NCSNIPS - Deep learning @ Edge using Intel's NCS
NIPS - Deep learning @ Edge using Intel's NCS
 
Deep learning for FinTech
Deep learning for FinTechDeep learning for FinTech
Deep learning for FinTech
 
Image verification assistant. By Polychronis Charitidis of CERTH-ITI
Image verification assistant. By Polychronis Charitidis of CERTH-ITIImage verification assistant. By Polychronis Charitidis of CERTH-ITI
Image verification assistant. By Polychronis Charitidis of CERTH-ITI
 
Capstone Design(2) 중간 발표
Capstone Design(2) 중간 발표Capstone Design(2) 중간 발표
Capstone Design(2) 중간 발표
 
モデル高速化百選
モデル高速化百選モデル高速化百選
モデル高速化百選
 
Ieee gold 2010 resta
Ieee gold 2010 restaIeee gold 2010 resta
Ieee gold 2010 resta
 

Andere mochten auch

CNNチュートリアル
CNNチュートリアルCNNチュートリアル
CNNチュートリアルIkuro Sato
 
ディープラーニングの車載応用に向けて
ディープラーニングの車載応用に向けてディープラーニングの車載応用に向けて
ディープラーニングの車載応用に向けてIkuro Sato
 
Go-ICP: グローバル最適(Globally optimal) なICPの解説
Go-ICP: グローバル最適(Globally optimal) なICPの解説Go-ICP: グローバル最適(Globally optimal) なICPの解説
Go-ICP: グローバル最適(Globally optimal) なICPの解説Yusuke Sekikawa
 
FLAT CAM: Replacing Lenses with Masks and Computationの解説
FLAT CAM: Replacing Lenses with Masks and Computationの解説FLAT CAM: Replacing Lenses with Masks and Computationの解説
FLAT CAM: Replacing Lenses with Masks and Computationの解説Yusuke Sekikawa
 
Deep Learning Chapter12
Deep Learning Chapter12Deep Learning Chapter12
Deep Learning Chapter12Kei Uchiumi
 
Vanishing Component Analysisの試作(補足)
Vanishing Component Analysisの試作(補足)Vanishing Component Analysisの試作(補足)
Vanishing Component Analysisの試作(補足)Hiroshi Tsukahara
 
Notes on the low rank matrix approximation of kernel
Notes on the low rank matrix approximation of kernelNotes on the low rank matrix approximation of kernel
Notes on the low rank matrix approximation of kernelHiroshi Tsukahara
 
DSIRNLP06 Nested Pitman-Yor Language Model
DSIRNLP06 Nested Pitman-Yor Language ModelDSIRNLP06 Nested Pitman-Yor Language Model
DSIRNLP06 Nested Pitman-Yor Language ModelKei Uchiumi
 
Vanishing Component Analysisの試作と簡単な実験
Vanishing Component Analysisの試作と簡単な実験Vanishing Component Analysisの試作と簡単な実験
Vanishing Component Analysisの試作と簡単な実験Hiroshi Tsukahara
 
Stochastic Process Overview (hypothesis)
Stochastic Process Overview (hypothesis)Stochastic Process Overview (hypothesis)
Stochastic Process Overview (hypothesis)Yoshiaki Sakakura
 
Halide, Darkroom - 並列化のためのソフトウェア・研究
Halide, Darkroom - 並列化のためのソフトウェア・研究Halide, Darkroom - 並列化のためのソフトウェア・研究
Halide, Darkroom - 並列化のためのソフトウェア・研究Yuichi Yoshida
 
論文紹介:Practical bayesian optimization of machine learning algorithms(nips2012)
論文紹介:Practical bayesian optimization of machine learning algorithms(nips2012)論文紹介:Practical bayesian optimization of machine learning algorithms(nips2012)
論文紹介:Practical bayesian optimization of machine learning algorithms(nips2012)Keisuke Uto
 

Andere mochten auch (20)

CNNチュートリアル
CNNチュートリアルCNNチュートリアル
CNNチュートリアル
 
ディープラーニングの車載応用に向けて
ディープラーニングの車載応用に向けてディープラーニングの車載応用に向けて
ディープラーニングの車載応用に向けて
 
Go-ICP: グローバル最適(Globally optimal) なICPの解説
Go-ICP: グローバル最適(Globally optimal) なICPの解説Go-ICP: グローバル最適(Globally optimal) なICPの解説
Go-ICP: グローバル最適(Globally optimal) なICPの解説
 
FLAT CAM: Replacing Lenses with Masks and Computationの解説
FLAT CAM: Replacing Lenses with Masks and Computationの解説FLAT CAM: Replacing Lenses with Masks and Computationの解説
FLAT CAM: Replacing Lenses with Masks and Computationの解説
 
Deep Learning Chapter12
Deep Learning Chapter12Deep Learning Chapter12
Deep Learning Chapter12
 
Vanishing Component Analysisの試作(補足)
Vanishing Component Analysisの試作(補足)Vanishing Component Analysisの試作(補足)
Vanishing Component Analysisの試作(補足)
 
Information extraction 1
Information extraction 1Information extraction 1
Information extraction 1
 
Notes on the low rank matrix approximation of kernel
Notes on the low rank matrix approximation of kernelNotes on the low rank matrix approximation of kernel
Notes on the low rank matrix approximation of kernel
 
Gitのすすめ
GitのすすめGitのすすめ
Gitのすすめ
 
DSIRNLP06 Nested Pitman-Yor Language Model
DSIRNLP06 Nested Pitman-Yor Language ModelDSIRNLP06 Nested Pitman-Yor Language Model
DSIRNLP06 Nested Pitman-Yor Language Model
 
Vanishing Component Analysisの試作と簡単な実験
Vanishing Component Analysisの試作と簡単な実験Vanishing Component Analysisの試作と簡単な実験
Vanishing Component Analysisの試作と簡単な実験
 
Pylm public
Pylm publicPylm public
Pylm public
 
Dsirnlp#7
Dsirnlp#7Dsirnlp#7
Dsirnlp#7
 
Stochastic Process Overview (hypothesis)
Stochastic Process Overview (hypothesis)Stochastic Process Overview (hypothesis)
Stochastic Process Overview (hypothesis)
 
マーク付き点過程
マーク付き点過程マーク付き点過程
マーク付き点過程
 
Extreme Learning Machine
Extreme Learning MachineExtreme Learning Machine
Extreme Learning Machine
 
Holonomic Gradient Descent
Holonomic Gradient DescentHolonomic Gradient Descent
Holonomic Gradient Descent
 
Halide, Darkroom - 並列化のためのソフトウェア・研究
Halide, Darkroom - 並列化のためのソフトウェア・研究Halide, Darkroom - 並列化のためのソフトウェア・研究
Halide, Darkroom - 並列化のためのソフトウェア・研究
 
RNNLM
RNNLMRNNLM
RNNLM
 
論文紹介:Practical bayesian optimization of machine learning algorithms(nips2012)
論文紹介:Practical bayesian optimization of machine learning algorithms(nips2012)論文紹介:Practical bayesian optimization of machine learning algorithms(nips2012)
論文紹介:Practical bayesian optimization of machine learning algorithms(nips2012)
 

Ähnlich wie Sparse Isotropic Hashing for Image Retrieval

IRJET - Conversion of Ancient Tamil Characters to Modern Tamil Characters
IRJET -  	  Conversion of Ancient Tamil Characters to Modern Tamil CharactersIRJET -  	  Conversion of Ancient Tamil Characters to Modern Tamil Characters
IRJET - Conversion of Ancient Tamil Characters to Modern Tamil CharactersIRJET Journal
 
Combinatorial testing in Japan
Combinatorial testing in JapanCombinatorial testing in Japan
Combinatorial testing in JapanKeizo Tatsumi
 
Software tools, crystal descriptors, and machine learning applied to material...
Software tools, crystal descriptors, and machine learning applied to material...Software tools, crystal descriptors, and machine learning applied to material...
Software tools, crystal descriptors, and machine learning applied to material...Anubhav Jain
 
Taguchi method for analysing the lathe machine
Taguchi method for analysing the lathe machineTaguchi method for analysing the lathe machine
Taguchi method for analysing the lathe machinechiragkolambe
 
IRJET- Experimental Study of Taguchi Vs GRA Parameters During CNC Boring in S...
IRJET- Experimental Study of Taguchi Vs GRA Parameters During CNC Boring in S...IRJET- Experimental Study of Taguchi Vs GRA Parameters During CNC Boring in S...
IRJET- Experimental Study of Taguchi Vs GRA Parameters During CNC Boring in S...IRJET Journal
 
[Paper Review] Personalized Top-N Sequential Recommendation via Convolutional...
[Paper Review] Personalized Top-N Sequential Recommendation via Convolutional...[Paper Review] Personalized Top-N Sequential Recommendation via Convolutional...
[Paper Review] Personalized Top-N Sequential Recommendation via Convolutional...Jihoo Kim
 
An experimental study on factors affecting Cold Extrusion of steels
An experimental study on factors affecting Cold Extrusion of steelsAn experimental study on factors affecting Cold Extrusion of steels
An experimental study on factors affecting Cold Extrusion of steelsIRJET Journal
 
Design and development of DrawBot using image processing
Design and development of DrawBot using image processing Design and development of DrawBot using image processing
Design and development of DrawBot using image processing IJECEIAES
 
Mlp mixer an all-mlp architecture for vision
Mlp mixer  an all-mlp architecture for visionMlp mixer  an all-mlp architecture for vision
Mlp mixer an all-mlp architecture for visionJaey Jeong
 
Comparison of signal smoothing techniques for use in embedded system for moni...
Comparison of signal smoothing techniques for use in embedded system for moni...Comparison of signal smoothing techniques for use in embedded system for moni...
Comparison of signal smoothing techniques for use in embedded system for moni...Dalton Valadares
 
2015-07-08 Paper 38 - ICVS Talk
2015-07-08 Paper 38 - ICVS Talk2015-07-08 Paper 38 - ICVS Talk
2015-07-08 Paper 38 - ICVS TalkThomas Sølund
 
Dynamic Simulation of Chemical Kinetics in Microcontroller
Dynamic Simulation of Chemical Kinetics in MicrocontrollerDynamic Simulation of Chemical Kinetics in Microcontroller
Dynamic Simulation of Chemical Kinetics in MicrocontrollerIJERA Editor
 
IEEE 2014 MATLAB IMAGE PROCESSING PROJECTS Scale adaptive dictionary learning
IEEE 2014 MATLAB IMAGE PROCESSING PROJECTS Scale adaptive dictionary learningIEEE 2014 MATLAB IMAGE PROCESSING PROJECTS Scale adaptive dictionary learning
IEEE 2014 MATLAB IMAGE PROCESSING PROJECTS Scale adaptive dictionary learningIEEEBEBTECHSTUDENTPROJECTS
 

Ähnlich wie Sparse Isotropic Hashing for Image Retrieval (20)

IRJET - Conversion of Ancient Tamil Characters to Modern Tamil Characters
IRJET -  	  Conversion of Ancient Tamil Characters to Modern Tamil CharactersIRJET -  	  Conversion of Ancient Tamil Characters to Modern Tamil Characters
IRJET - Conversion of Ancient Tamil Characters to Modern Tamil Characters
 
upload test2
upload test2upload test2
upload test2
 
upload test
upload testupload test
upload test
 
upload test1
upload test1upload test1
upload test1
 
upload test
upload testupload test
upload test
 
upload test2
upload test2upload test2
upload test2
 
Combinatorial testing in Japan
Combinatorial testing in JapanCombinatorial testing in Japan
Combinatorial testing in Japan
 
Software tools, crystal descriptors, and machine learning applied to material...
Software tools, crystal descriptors, and machine learning applied to material...Software tools, crystal descriptors, and machine learning applied to material...
Software tools, crystal descriptors, and machine learning applied to material...
 
Taguchi method for analysing the lathe machine
Taguchi method for analysing the lathe machineTaguchi method for analysing the lathe machine
Taguchi method for analysing the lathe machine
 
IRJET- Experimental Study of Taguchi Vs GRA Parameters During CNC Boring in S...
IRJET- Experimental Study of Taguchi Vs GRA Parameters During CNC Boring in S...IRJET- Experimental Study of Taguchi Vs GRA Parameters During CNC Boring in S...
IRJET- Experimental Study of Taguchi Vs GRA Parameters During CNC Boring in S...
 
[Paper Review] Personalized Top-N Sequential Recommendation via Convolutional...
[Paper Review] Personalized Top-N Sequential Recommendation via Convolutional...[Paper Review] Personalized Top-N Sequential Recommendation via Convolutional...
[Paper Review] Personalized Top-N Sequential Recommendation via Convolutional...
 
An experimental study on factors affecting Cold Extrusion of steels
An experimental study on factors affecting Cold Extrusion of steelsAn experimental study on factors affecting Cold Extrusion of steels
An experimental study on factors affecting Cold Extrusion of steels
 
Bat Algorithm_Basics
Bat Algorithm_BasicsBat Algorithm_Basics
Bat Algorithm_Basics
 
SAE/OCDM System
SAE/OCDM System SAE/OCDM System
SAE/OCDM System
 
Design and development of DrawBot using image processing
Design and development of DrawBot using image processing Design and development of DrawBot using image processing
Design and development of DrawBot using image processing
 
Mlp mixer an all-mlp architecture for vision
Mlp mixer  an all-mlp architecture for visionMlp mixer  an all-mlp architecture for vision
Mlp mixer an all-mlp architecture for vision
 
Comparison of signal smoothing techniques for use in embedded system for moni...
Comparison of signal smoothing techniques for use in embedded system for moni...Comparison of signal smoothing techniques for use in embedded system for moni...
Comparison of signal smoothing techniques for use in embedded system for moni...
 
2015-07-08 Paper 38 - ICVS Talk
2015-07-08 Paper 38 - ICVS Talk2015-07-08 Paper 38 - ICVS Talk
2015-07-08 Paper 38 - ICVS Talk
 
Dynamic Simulation of Chemical Kinetics in Microcontroller
Dynamic Simulation of Chemical Kinetics in MicrocontrollerDynamic Simulation of Chemical Kinetics in Microcontroller
Dynamic Simulation of Chemical Kinetics in Microcontroller
 
IEEE 2014 MATLAB IMAGE PROCESSING PROJECTS Scale adaptive dictionary learning
IEEE 2014 MATLAB IMAGE PROCESSING PROJECTS Scale adaptive dictionary learningIEEE 2014 MATLAB IMAGE PROCESSING PROJECTS Scale adaptive dictionary learning
IEEE 2014 MATLAB IMAGE PROCESSING PROJECTS Scale adaptive dictionary learning
 

Kürzlich hochgeladen

How to Effectively Monitor SD-WAN and SASE Environments with ThousandEyes
How to Effectively Monitor SD-WAN and SASE Environments with ThousandEyesHow to Effectively Monitor SD-WAN and SASE Environments with ThousandEyes
How to Effectively Monitor SD-WAN and SASE Environments with ThousandEyesThousandEyes
 
Digital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptxDigital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptxLoriGlavin3
 
Sample pptx for embedding into website for demo
Sample pptx for embedding into website for demoSample pptx for embedding into website for demo
Sample pptx for embedding into website for demoHarshalMandlekar2
 
TrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data PrivacyTrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data PrivacyTrustArc
 
Generative Artificial Intelligence: How generative AI works.pdf
Generative Artificial Intelligence: How generative AI works.pdfGenerative Artificial Intelligence: How generative AI works.pdf
Generative Artificial Intelligence: How generative AI works.pdfIngrid Airi González
 
(How to Program) Paul Deitel, Harvey Deitel-Java How to Program, Early Object...
(How to Program) Paul Deitel, Harvey Deitel-Java How to Program, Early Object...(How to Program) Paul Deitel, Harvey Deitel-Java How to Program, Early Object...
(How to Program) Paul Deitel, Harvey Deitel-Java How to Program, Early Object...AliaaTarek5
 
Why device, WIFI, and ISP insights are crucial to supporting remote Microsoft...
Why device, WIFI, and ISP insights are crucial to supporting remote Microsoft...Why device, WIFI, and ISP insights are crucial to supporting remote Microsoft...
Why device, WIFI, and ISP insights are crucial to supporting remote Microsoft...panagenda
 
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptx
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptxUse of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptx
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptxLoriGlavin3
 
Emixa Mendix Meetup 11 April 2024 about Mendix Native development
Emixa Mendix Meetup 11 April 2024 about Mendix Native developmentEmixa Mendix Meetup 11 April 2024 about Mendix Native development
Emixa Mendix Meetup 11 April 2024 about Mendix Native developmentPim van der Noll
 
TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024Lonnie McRorey
 
Enhancing User Experience - Exploring the Latest Features of Tallyman Axis Lo...
Enhancing User Experience - Exploring the Latest Features of Tallyman Axis Lo...Enhancing User Experience - Exploring the Latest Features of Tallyman Axis Lo...
Enhancing User Experience - Exploring the Latest Features of Tallyman Axis Lo...Scott Andery
 
The Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsThe Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsPixlogix Infotech
 
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptxThe Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptxLoriGlavin3
 
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024BookNet Canada
 
What is DBT - The Ultimate Data Build Tool.pdf
What is DBT - The Ultimate Data Build Tool.pdfWhat is DBT - The Ultimate Data Build Tool.pdf
What is DBT - The Ultimate Data Build Tool.pdfMounikaPolabathina
 
Scale your database traffic with Read & Write split using MySQL Router
Scale your database traffic with Read & Write split using MySQL RouterScale your database traffic with Read & Write split using MySQL Router
Scale your database traffic with Read & Write split using MySQL RouterMydbops
 
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptx
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptxPasskey Providers and Enabling Portability: FIDO Paris Seminar.pptx
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptxLoriGlavin3
 
Take control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteTake control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteDianaGray10
 
2024 April Patch Tuesday
2024 April Patch Tuesday2024 April Patch Tuesday
2024 April Patch TuesdayIvanti
 
Assure Ecommerce and Retail Operations Uptime with ThousandEyes
Assure Ecommerce and Retail Operations Uptime with ThousandEyesAssure Ecommerce and Retail Operations Uptime with ThousandEyes
Assure Ecommerce and Retail Operations Uptime with ThousandEyesThousandEyes
 

Kürzlich hochgeladen (20)

How to Effectively Monitor SD-WAN and SASE Environments with ThousandEyes
How to Effectively Monitor SD-WAN and SASE Environments with ThousandEyesHow to Effectively Monitor SD-WAN and SASE Environments with ThousandEyes
How to Effectively Monitor SD-WAN and SASE Environments with ThousandEyes
 
Digital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptxDigital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptx
 
Sample pptx for embedding into website for demo
Sample pptx for embedding into website for demoSample pptx for embedding into website for demo
Sample pptx for embedding into website for demo
 
TrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data PrivacyTrustArc Webinar - How to Build Consumer Trust Through Data Privacy
TrustArc Webinar - How to Build Consumer Trust Through Data Privacy
 
Generative Artificial Intelligence: How generative AI works.pdf
Generative Artificial Intelligence: How generative AI works.pdfGenerative Artificial Intelligence: How generative AI works.pdf
Generative Artificial Intelligence: How generative AI works.pdf
 
(How to Program) Paul Deitel, Harvey Deitel-Java How to Program, Early Object...
(How to Program) Paul Deitel, Harvey Deitel-Java How to Program, Early Object...(How to Program) Paul Deitel, Harvey Deitel-Java How to Program, Early Object...
(How to Program) Paul Deitel, Harvey Deitel-Java How to Program, Early Object...
 
Why device, WIFI, and ISP insights are crucial to supporting remote Microsoft...
Why device, WIFI, and ISP insights are crucial to supporting remote Microsoft...Why device, WIFI, and ISP insights are crucial to supporting remote Microsoft...
Why device, WIFI, and ISP insights are crucial to supporting remote Microsoft...
 
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptx
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptxUse of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptx
Use of FIDO in the Payments and Identity Landscape: FIDO Paris Seminar.pptx
 
Emixa Mendix Meetup 11 April 2024 about Mendix Native development
Emixa Mendix Meetup 11 April 2024 about Mendix Native developmentEmixa Mendix Meetup 11 April 2024 about Mendix Native development
Emixa Mendix Meetup 11 April 2024 about Mendix Native development
 
TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024
 
Enhancing User Experience - Exploring the Latest Features of Tallyman Axis Lo...
Enhancing User Experience - Exploring the Latest Features of Tallyman Axis Lo...Enhancing User Experience - Exploring the Latest Features of Tallyman Axis Lo...
Enhancing User Experience - Exploring the Latest Features of Tallyman Axis Lo...
 
The Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and ConsThe Ultimate Guide to Choosing WordPress Pros and Cons
The Ultimate Guide to Choosing WordPress Pros and Cons
 
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptxThe Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
The Role of FIDO in a Cyber Secure Netherlands: FIDO Paris Seminar.pptx
 
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
 
What is DBT - The Ultimate Data Build Tool.pdf
What is DBT - The Ultimate Data Build Tool.pdfWhat is DBT - The Ultimate Data Build Tool.pdf
What is DBT - The Ultimate Data Build Tool.pdf
 
Scale your database traffic with Read & Write split using MySQL Router
Scale your database traffic with Read & Write split using MySQL RouterScale your database traffic with Read & Write split using MySQL Router
Scale your database traffic with Read & Write split using MySQL Router
 
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptx
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptxPasskey Providers and Enabling Portability: FIDO Paris Seminar.pptx
Passkey Providers and Enabling Portability: FIDO Paris Seminar.pptx
 
Take control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteTake control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test Suite
 
2024 April Patch Tuesday
2024 April Patch Tuesday2024 April Patch Tuesday
2024 April Patch Tuesday
 
Assure Ecommerce and Retail Operations Uptime with ThousandEyes
Assure Ecommerce and Retail Operations Uptime with ThousandEyesAssure Ecommerce and Retail Operations Uptime with ThousandEyes
Assure Ecommerce and Retail Operations Uptime with ThousandEyes
 

Sparse Isotropic Hashing for Image Retrieval

  • 1. Sparse Isotropic Hashing Ikuro Sato, Mitsuru Ambai, Koichiro Suzuki Denso IT Laboratory, Inc. {isato, manbai, ksuzuki}@d-itlab.co.jp 8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 1/28 Presented at MIRU 2013, Japan. Peer reviewed paper available at http://www.am.sanken.osaka-u.ac.jp/CVA/
  • 2. • Introduction • Proposed method • Experiment 8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 2/36
  • 3. Practical issues of large-scale image retrieval • ex) descriptor-matching approach millions of sums-of-product / query ? slow query image query image DB: ~108 images 8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 3/28
  • 4. Potential solution: descriptor binarization computational time of similarity real 512 bit 256 bit 128 bit 64 bit 32 bit binary codes1 8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 4/28
  • 5. Binarization by hash functions 1. supervised – uses known point-to-point correspondences • ex) Ambai et al, 2012. 2. unsupervised – intends to preserve similarities among the original real vectors 8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 5/28
  • 6. Popular hash function ex) Random Proj. (Goemans et al, 1995) Very Sparse Rand. Proj. (Li et al, 2006) Sequential Proj. (Wang et al, 2010) 8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. Iterative Quantization (Gong et al, 2011) Isotropic Hashing (Kong et al, 2012) this work state-of-the-art 6/28
  • 7. Most related work: Isotropic Hashing (Kong et al, 2012) 1. orthonormality 2. isotropic variance 8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 7/28
  • 8. Most related work: Isotropic Hashing (Kong et al, 2012) 1. orthonormality 2. isotropic variance Robust to noise from spherically symmetric distribution. 8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 8/28
  • 9. Learning of Isotropic Hashing • Lift and Projection (LP) algorithm isotropic orthogonal Gradient Flow algorithm omitted. intersection 8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 9/28 1) PCA:
  • 10. Under-constrained problem It’s more natural to impose additional conditions to make the problem over-constrained. our motivation 8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 10/28
  • 11. Our contribution 8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 11/28
  • 12. • Introduction • Proposed method • Experiment 8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 12/36
  • 13. Problem setup 1. rotational matrix 2. isotropic variance 3. sparsity 8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 13/28
  • 14. Condition-1: Special orthogonal group -1 1 0 8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 14/28
  • 15. Condition-2: Cost function for isotropic variance Exact solutions exist according to the Schur-Horn Theorem (AJM1954). 8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 15/28
  • 16. 8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 16/28
  • 17. Our optimization problem 8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 17/28
  • 18. Algorithm Sparse Isotropic Hashing (SIH) • Repeat until convergence. endfor notations simplified 8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 18/28
  • 19. Illustration of the optimization process 8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 19/28
  • 20. • Introduction • Proposed method • Experiment 8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 20/36
  • 21. Dataset etc. * M. Ambai and I. Sato, “Fast binary coding of local descriptors based on supervised learning” (MIRU2012). descriptor query set (u=1) training set (u=2, 3, 4) test set (u=5, 6) CARD (Ambai et al, 2011) without binarization 12896 50053 25238 # local descriptors 8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 21/28
  • 22. Evaluation criterion • Mean Average Precision (mAP) – expected value of area under Precision-Recall curve 8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. precision recall 1.0 Average Precision 22/28
  • 23. Methods compared All methods use 8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 23/28 state-of-the-art
  • 24. mAP for CARD 8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 24/28
  • 25. mAP for CARD 8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 25/28
  • 26. mAP for CARD almost on top 8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 26/28
  • 27. mAP for CARD 10% drop in mAP, 20x faster coding env.: VS2010, C program 8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 27/28
  • 28. Conclusion Isotropic Hashing (Kong et al, 2012): highly under-constrained 8/1/2013 Copyright (C) 2013 DENSO IT LABORATORY, INC. All Rights Reserved. 28/28