SlideShare una empresa de Scribd logo
1 de 42
Descargar para leer sin conexión
The Duality of Object Retrieval:

Unsupervised and Supervised
Approaches
TUAN NGUYEN ANH
THE UNIVERSITY OF TOKYO
Index
•  Part 1: Basic Object Retrieval
Ø Unsupervised approaches
•  Part 2: State-of-the-art results
•  Part 3: Future attempts
Ø Duality & supervised approaches
•  Conclusion
2
Part 1: Basic Object Retrieval
Object Retrieval 4
?	
1st	
2nd	
3rd	
4th
5
Similar
images
Related
info
Source: https://www.yandex.com/images
6
Key words for images
Similar
images
Source: https://www.google.com/imghp
Related
info
7
Pinterest: Zoom-in Search 8
Source: https://www.pinterest.com/
Overview of the system 9
Query	
Database	
Matching	
Features
Features in object retrieval 10
Query	
Database	
Matching	
Features
Local features
•  SIFT [Lowe, 1999, 2004]
•  HOG [Dalal & Triggs, 2005]
11
Global and deep features
•  GIST features [Oliva et al., 2001]
Ø Describe the images by spectral information
•  Deep features
Ø Extracted from neural networks
12
[Krizhevsky et al., 2012]
Aggregated Features
•  BoF [Sivic et al., 2003]
•  Hamming Embedding [Jégou et al., 2008]
•  Fisher Vector [Perronnin et al., 2007]
•  VLAD [Jégou et al., 2012]
13
Bag of Features (BoF)
•  Cluster local descriptors to build a dictionary.
•  Compute the BoF vector as a histogram of
visual words.
14
Images	
c2
c3
Dictionary	
Bag of Features	
[Sivic et al., 2003]
Hamming Embedding
•  Each local descriptors set of an image will be
encoded by a binary signature.
15
[Jégou et al., 2008]
Fisher Vector (FV)
•  Cluster the local descriptors by GMM
•  Fisher Kernel
•  Fisher Vector
16
Images	 Local descriptors	
GMM	
Fisher Vector	
[Perronnin et al., 2007]
VLAD
•  Replace the GMM in FV by k-means clustering
•  Approximate FV by
17
Images	 Local descriptors	
K-means	
VLAD Vector	
[Jégou et al., 2012]
Overview of the system 18
Query	
Database	
Matching	
Features
Distances and similarities
•  Euclidean distances
•  Hamming distances
•  Inner product
•  Approximated distances (ADC):
Ø Distance between query vector and compressed
database vector.
Ø [Jégou et al., 2011]
19
Nearest neighbor search 20
Query	
Database	
Matching,
Nearest
neighbor search	
Features
Nearest neighbor search 21
Nearest
neighbor
Indexing and compressing data
•  Coarse-to-fine strategy
Ø Use quantization techniques to build an inverted
file (IVF)
22
c1 1 3
c2 2
c3 4 5 6
id code
m bytes
c2
c3
Inverted File
Compressed vectorFaster
search
Better memory
footprint
[Jégou et al., 2011]
Quantization techniques
•  Compress the data for
better memory footprint
•  Search accuracy is
acceptable with
appropriate parameters
23
Recall = 95% with 64 bits code
[Jégou et al., 2011]	
3
5 6
id code
m bytes
Feature processing
•  Square rooting [Arandjelovic & Zisserman,
2012]
•  L2-normalization [Jain et al., 2012]
•  Centralization [Tolias et al., 2013]
•  Down-weight highly populated cells in
aggregation [Jégou et al., 2009]
•  Whitening [Jégou et al., 2010]
24
Image processing: re-ranking
•  Estimate a transformation between the query
region and each target image.
•  Target images are re-ranked based on the
discriminability of the spatially verified visual
words.
25
mAP with BoF:
0.618→0.645
[Philbin et al., 2007]	
Dataset: Oxford
Buildings	
Queries
Image processing: query expansion 26
mAP with BoF:
0.645→0.696
[Chum et al., 2007]	
•  Requery after reconstructing the original
query.
•  The new query is constructed from verified
query in the first time retrieval.
Dataset: Oxford
Buildings
Part 2: State-of-the-art results
Nearest neighbor search
•  Datasets: 1M~1B vectors with ground truth
data
Ø BIGANN dataset: http://corpus-texmex.irisa.fr/
•  Evaluation
Ø recall@R = the proportion of queries with NN
ranked in top-R results.
28
c1 1 3
c2 2
c3 4 5 6
id code
m bytes
c2
c3
Inverted File
Compressed vector
Quantization techniques
•  Additive Quantization
[Babenko et al., 2014]
•  Approximate a vector by
the sum of codewords.
•  Learn codewords by an
iterative optimization.
•  Composite Quantization
[Zhang et al., 2014]
•  Minimize the
orthogonality of the
approximation.
29
Indexing techniques
•  Multi-indexing [Babenko et al., 2012, 2015]
•  Performance in a dataset of one billion SIFT
vectors
Ø Memory: 12 GB
Ø Search time: 2 ms/query
Ø recall@100 = 70%
30
Image search
•  Datasets: Oxford building dataset [Philbin et
al., 2007]
•  Evaluation
Ø mAP: Mean average precision for a set of queries
is the mean of the average precision scores for
each query.
31
Selective Match Kernel
•  [Tolias et al., 2013]
•  Apply the power normalization to each VLAD
component to improve the accuracy.
•  Use hashing to reduce the memory footprint.
•  mAP = 0.817 on Oxford5K dataset [Philbin et al., 2007]
32
Neural Codes
•  [Babenko et al., 2014]
•  Attempt to use features that are extracted from
neural network to object retrieval.
•  Features are fine-tuned.
•  mAP = 0.435 with fc6 features on Oxford5K
dataset.
33
Sum-pooled convolutional features
•  [Babenko et al., 2015]
•  Deep features are sum-pooled and Gaussian
weighted to improve the accuracy.
•  mAP = 0.657 on Oxford5K dataset.
34
Summary of image retrieval results 35
•  Search framework with deep features in object
retrieval still need to be improved.
Method	 Feature	 Framework	 mAP	
ASMK [Tolias et al., 2013]	 SIFT	 VLAD	 0.817	
Neural codes [Babenko et al., 2014]	 Deep features	 -	 0.435	
SPoC [Babenko et al., 2015]	 Deep features	 SPoC	 0.657
Part 3: Future attempts
Attempts on current topics
•  Improve the features:
Ø Feature fusion
Ø Find new match kernels
Ø Improve the system with deep features?
•  Improve the distance metrics and NN search.
37
Dual-process system 38
•  [Stanovich et al., 1999, 2004]
Fast, high
capacity, implicit
knowledge and
basic emotions
only . 	
Slow, limited
capacity, explicit
knowledge and
complicated
emotions.
Supervised Object Retrieval?
•  More than just apply the deep features into
retrieval.
•  Learning while searching?
•  Learning with feedback?
39
The Duality of Object Retrieval
•  The collaboration between unsupervised
learning and supervised learning in object
retrieval.
40
[Stanovich et al., 1999, 2004]
Conclusion
•  Basic Object Retrieval
Ø Features: SIFT, HOG, GIST, deep features
Ø Distance metrics and NN search
Ø Hamming Embedding and Aggregation
Ø Pre-processing and post-processing
•  State-of-the-art results
•  Future attempts: Duality & Supervised &
Unsupervised?
41
Thank you for listening

Más contenido relacionado

La actualidad más candente

Parn pyramidal+affine+regression+networks+for+dense+semantic+correspondence
Parn pyramidal+affine+regression+networks+for+dense+semantic+correspondenceParn pyramidal+affine+regression+networks+for+dense+semantic+correspondence
Parn pyramidal+affine+regression+networks+for+dense+semantic+correspondenceNAVER Engineering
 
[CVPR2020] Simple but effective image enhancement techniques
[CVPR2020] Simple but effective image enhancement techniques[CVPR2020] Simple but effective image enhancement techniques
[CVPR2020] Simple but effective image enhancement techniquesJaeJun Yoo
 
Learning Based Single Frame Image Super-resolution Using Fast Discrete Curvel...
Learning Based Single Frame Image Super-resolution Using Fast Discrete Curvel...Learning Based Single Frame Image Super-resolution Using Fast Discrete Curvel...
Learning Based Single Frame Image Super-resolution Using Fast Discrete Curvel...CSCJournals
 
Learning Anticipation via Spiking Networks: Application to Navigation Control
Learning Anticipation via Spiking Networks: Application to Navigation ControlLearning Anticipation via Spiking Networks: Application to Navigation Control
Learning Anticipation via Spiking Networks: Application to Navigation ControlSeonghyun Kim
 
Joint super resolution and denoising from a single depth image
Joint super resolution and denoising from a single depth imageJoint super resolution and denoising from a single depth image
Joint super resolution and denoising from a single depth imageLogicMindtech Nologies
 
A goal-directed spatial navigation model using forward trajectory planning ba...
A goal-directed spatial navigation model using forward trajectory planning ba...A goal-directed spatial navigation model using forward trajectory planning ba...
A goal-directed spatial navigation model using forward trajectory planning ba...Seonghyun Kim
 
Computational Cognitive Models of Spatial Memory in Navigation Space: A review
Computational Cognitive Models of Spatial Memory in Navigation Space: A reviewComputational Cognitive Models of Spatial Memory in Navigation Space: A review
Computational Cognitive Models of Spatial Memory in Navigation Space: A reviewSeonghyun Kim
 
A Review of Recent Texture Classification: Methods
A Review of Recent Texture Classification: MethodsA Review of Recent Texture Classification: Methods
A Review of Recent Texture Classification: MethodsIOSR Journals
 
[PR12] Generative Models as Distributions of Functions
[PR12] Generative Models as Distributions of Functions[PR12] Generative Models as Distributions of Functions
[PR12] Generative Models as Distributions of FunctionsJaeJun Yoo
 
Enhancement of Old Images and Documents by Digital Image Processing Techniques.
Enhancement of Old Images and Documents by Digital Image Processing Techniques.Enhancement of Old Images and Documents by Digital Image Processing Techniques.
Enhancement of Old Images and Documents by Digital Image Processing Techniques.Triloki Gupta
 
A Brief History of Object Detection / Tommi Kerola
A Brief History of Object Detection / Tommi KerolaA Brief History of Object Detection / Tommi Kerola
A Brief History of Object Detection / Tommi KerolaPreferred Networks
 
CV_Chap 6 Motion Representation
CV_Chap 6 Motion RepresentationCV_Chap 6 Motion Representation
CV_Chap 6 Motion RepresentationKhushali Kathiriya
 
The hippocampo-cortical loop: Spatio-temporal learning and goal-oriented plan...
The hippocampo-cortical loop: Spatio-temporal learning and goal-oriented plan...The hippocampo-cortical loop: Spatio-temporal learning and goal-oriented plan...
The hippocampo-cortical loop: Spatio-temporal learning and goal-oriented plan...Seonghyun Kim
 

La actualidad más candente (13)

Parn pyramidal+affine+regression+networks+for+dense+semantic+correspondence
Parn pyramidal+affine+regression+networks+for+dense+semantic+correspondenceParn pyramidal+affine+regression+networks+for+dense+semantic+correspondence
Parn pyramidal+affine+regression+networks+for+dense+semantic+correspondence
 
[CVPR2020] Simple but effective image enhancement techniques
[CVPR2020] Simple but effective image enhancement techniques[CVPR2020] Simple but effective image enhancement techniques
[CVPR2020] Simple but effective image enhancement techniques
 
Learning Based Single Frame Image Super-resolution Using Fast Discrete Curvel...
Learning Based Single Frame Image Super-resolution Using Fast Discrete Curvel...Learning Based Single Frame Image Super-resolution Using Fast Discrete Curvel...
Learning Based Single Frame Image Super-resolution Using Fast Discrete Curvel...
 
Learning Anticipation via Spiking Networks: Application to Navigation Control
Learning Anticipation via Spiking Networks: Application to Navigation ControlLearning Anticipation via Spiking Networks: Application to Navigation Control
Learning Anticipation via Spiking Networks: Application to Navigation Control
 
Joint super resolution and denoising from a single depth image
Joint super resolution and denoising from a single depth imageJoint super resolution and denoising from a single depth image
Joint super resolution and denoising from a single depth image
 
A goal-directed spatial navigation model using forward trajectory planning ba...
A goal-directed spatial navigation model using forward trajectory planning ba...A goal-directed spatial navigation model using forward trajectory planning ba...
A goal-directed spatial navigation model using forward trajectory planning ba...
 
Computational Cognitive Models of Spatial Memory in Navigation Space: A review
Computational Cognitive Models of Spatial Memory in Navigation Space: A reviewComputational Cognitive Models of Spatial Memory in Navigation Space: A review
Computational Cognitive Models of Spatial Memory in Navigation Space: A review
 
A Review of Recent Texture Classification: Methods
A Review of Recent Texture Classification: MethodsA Review of Recent Texture Classification: Methods
A Review of Recent Texture Classification: Methods
 
[PR12] Generative Models as Distributions of Functions
[PR12] Generative Models as Distributions of Functions[PR12] Generative Models as Distributions of Functions
[PR12] Generative Models as Distributions of Functions
 
Enhancement of Old Images and Documents by Digital Image Processing Techniques.
Enhancement of Old Images and Documents by Digital Image Processing Techniques.Enhancement of Old Images and Documents by Digital Image Processing Techniques.
Enhancement of Old Images and Documents by Digital Image Processing Techniques.
 
A Brief History of Object Detection / Tommi Kerola
A Brief History of Object Detection / Tommi KerolaA Brief History of Object Detection / Tommi Kerola
A Brief History of Object Detection / Tommi Kerola
 
CV_Chap 6 Motion Representation
CV_Chap 6 Motion RepresentationCV_Chap 6 Motion Representation
CV_Chap 6 Motion Representation
 
The hippocampo-cortical loop: Spatio-temporal learning and goal-oriented plan...
The hippocampo-cortical loop: Spatio-temporal learning and goal-oriented plan...The hippocampo-cortical loop: Spatio-temporal learning and goal-oriented plan...
The hippocampo-cortical loop: Spatio-temporal learning and goal-oriented plan...
 

Destacado

Style-Finder Fine-Grained Clothing Style Detection and Retrieval
Style-Finder Fine-Grained Clothing Style Detection and RetrievalStyle-Finder Fine-Grained Clothing Style Detection and Retrieval
Style-Finder Fine-Grained Clothing Style Detection and RetrievalWei Di
 
Lec-08 Feature Aggregation II: Fisher Vector, AKULA and Super Vector
Lec-08 Feature Aggregation II: Fisher Vector, AKULA and Super VectorLec-08 Feature Aggregation II: Fisher Vector, AKULA and Super Vector
Lec-08 Feature Aggregation II: Fisher Vector, AKULA and Super VectorUnited States Air Force Academy
 
Fisher Vectorによる画像認識
Fisher Vectorによる画像認識Fisher Vectorによる画像認識
Fisher Vectorによる画像認識Takao Yamanaka
 
Image Retrieval with Fisher Vectors of Binary Features (MIRU'14)
Image Retrieval with Fisher Vectors of Binary Features (MIRU'14)Image Retrieval with Fisher Vectors of Binary Features (MIRU'14)
Image Retrieval with Fisher Vectors of Binary Features (MIRU'14)Yusuke Uchida
 

Destacado (6)

Style-Finder Fine-Grained Clothing Style Detection and Retrieval
Style-Finder Fine-Grained Clothing Style Detection and RetrievalStyle-Finder Fine-Grained Clothing Style Detection and Retrieval
Style-Finder Fine-Grained Clothing Style Detection and Retrieval
 
Lec-08 Feature Aggregation II: Fisher Vector, AKULA and Super Vector
Lec-08 Feature Aggregation II: Fisher Vector, AKULA and Super VectorLec-08 Feature Aggregation II: Fisher Vector, AKULA and Super Vector
Lec-08 Feature Aggregation II: Fisher Vector, AKULA and Super Vector
 
ICME 2013
ICME 2013ICME 2013
ICME 2013
 
Fisher Vectorによる画像認識
Fisher Vectorによる画像認識Fisher Vectorによる画像認識
Fisher Vectorによる画像認識
 
Image Retrieval with Fisher Vectors of Binary Features (MIRU'14)
Image Retrieval with Fisher Vectors of Binary Features (MIRU'14)Image Retrieval with Fisher Vectors of Binary Features (MIRU'14)
Image Retrieval with Fisher Vectors of Binary Features (MIRU'14)
 
Ppt for national conference
Ppt for national conferencePpt for national conference
Ppt for national conference
 

Similar a A Survey about Object Retrieval

Presentation of master thesis
Presentation of master thesisPresentation of master thesis
Presentation of master thesisSeoung-Ho Choi
 
Evolving a Medical Image Similarity Search
Evolving a Medical Image Similarity SearchEvolving a Medical Image Similarity Search
Evolving a Medical Image Similarity SearchSujit Pal
 
[RSS2023] Local Object Crop Collision Network for Efficient Simulation
[RSS2023] Local Object Crop Collision Network for Efficient Simulation[RSS2023] Local Object Crop Collision Network for Efficient Simulation
[RSS2023] Local Object Crop Collision Network for Efficient SimulationDongwonSon1
 
Image Co-segmentation via Saliency Co-fusion
Image Co-segmentation via Saliency Co-fusionImage Co-segmentation via Saliency Co-fusion
Image Co-segmentation via Saliency Co-fusionKoteswar Rao Jerripothula
 
A Novel Method for Content Based Image Retrieval using Local Features and SVM...
A Novel Method for Content Based Image Retrieval using Local Features and SVM...A Novel Method for Content Based Image Retrieval using Local Features and SVM...
A Novel Method for Content Based Image Retrieval using Local Features and SVM...IRJET Journal
 
Improving the Accuracy of Object Based Supervised Image Classification using ...
Improving the Accuracy of Object Based Supervised Image Classification using ...Improving the Accuracy of Object Based Supervised Image Classification using ...
Improving the Accuracy of Object Based Supervised Image Classification using ...CSCJournals
 
Lecture 29 Convolutional Neural Networks - Computer Vision Spring2015
Lecture 29 Convolutional Neural Networks -  Computer Vision Spring2015Lecture 29 Convolutional Neural Networks -  Computer Vision Spring2015
Lecture 29 Convolutional Neural Networks - Computer Vision Spring2015Jia-Bin Huang
 
Implementation of high performance feature extraction method using oriented f...
Implementation of high performance feature extraction method using oriented f...Implementation of high performance feature extraction method using oriented f...
Implementation of high performance feature extraction method using oriented f...eSAT Journals
 
Asking Clarifying Questions in Open-Domain Information-Seeking Conversations
Asking Clarifying Questions in Open-Domain Information-Seeking ConversationsAsking Clarifying Questions in Open-Domain Information-Seeking Conversations
Asking Clarifying Questions in Open-Domain Information-Seeking ConversationsMohammad Aliannejadi
 
Content Based Image Retrieval
Content Based Image RetrievalContent Based Image Retrieval
Content Based Image RetrievalSOURAV KAR
 
Efficient Neural Network Architecture for Image Classfication
Efficient Neural Network Architecture for Image ClassficationEfficient Neural Network Architecture for Image Classfication
Efficient Neural Network Architecture for Image ClassficationYogendra Tamang
 
Retrieval of Monuments Images Through ACO Optimization Approach
Retrieval of Monuments Images Through ACO Optimization ApproachRetrieval of Monuments Images Through ACO Optimization Approach
Retrieval of Monuments Images Through ACO Optimization ApproachIRJET Journal
 
Microsoft COCO: Common Objects in Context
Microsoft COCO: Common Objects in Context Microsoft COCO: Common Objects in Context
Microsoft COCO: Common Objects in Context KhalidKhan412
 
A Benchmark for Simulated Manipulation
A Benchmark for Simulated ManipulationA Benchmark for Simulated Manipulation
A Benchmark for Simulated ManipulationJack Collins
 
Reduce Query Time Up to 60% with Selective Search
Reduce Query Time Up to 60% with Selective SearchReduce Query Time Up to 60% with Selective Search
Reduce Query Time Up to 60% with Selective SearchLucidworks
 

Similar a A Survey about Object Retrieval (20)

CBIR with RF
CBIR with RFCBIR with RF
CBIR with RF
 
Presentation of master thesis
Presentation of master thesisPresentation of master thesis
Presentation of master thesis
 
Evolving a Medical Image Similarity Search
Evolving a Medical Image Similarity SearchEvolving a Medical Image Similarity Search
Evolving a Medical Image Similarity Search
 
ISM2014
ISM2014ISM2014
ISM2014
 
[RSS2023] Local Object Crop Collision Network for Efficient Simulation
[RSS2023] Local Object Crop Collision Network for Efficient Simulation[RSS2023] Local Object Crop Collision Network for Efficient Simulation
[RSS2023] Local Object Crop Collision Network for Efficient Simulation
 
Image Co-segmentation via Saliency Co-fusion
Image Co-segmentation via Saliency Co-fusionImage Co-segmentation via Saliency Co-fusion
Image Co-segmentation via Saliency Co-fusion
 
A Novel Method for Content Based Image Retrieval using Local Features and SVM...
A Novel Method for Content Based Image Retrieval using Local Features and SVM...A Novel Method for Content Based Image Retrieval using Local Features and SVM...
A Novel Method for Content Based Image Retrieval using Local Features and SVM...
 
ICPC06.ppt
ICPC06.pptICPC06.ppt
ICPC06.ppt
 
Improving the Accuracy of Object Based Supervised Image Classification using ...
Improving the Accuracy of Object Based Supervised Image Classification using ...Improving the Accuracy of Object Based Supervised Image Classification using ...
Improving the Accuracy of Object Based Supervised Image Classification using ...
 
Lecture 29 Convolutional Neural Networks - Computer Vision Spring2015
Lecture 29 Convolutional Neural Networks -  Computer Vision Spring2015Lecture 29 Convolutional Neural Networks -  Computer Vision Spring2015
Lecture 29 Convolutional Neural Networks - Computer Vision Spring2015
 
Implementation of high performance feature extraction method using oriented f...
Implementation of high performance feature extraction method using oriented f...Implementation of high performance feature extraction method using oriented f...
Implementation of high performance feature extraction method using oriented f...
 
Asking Clarifying Questions in Open-Domain Information-Seeking Conversations
Asking Clarifying Questions in Open-Domain Information-Seeking ConversationsAsking Clarifying Questions in Open-Domain Information-Seeking Conversations
Asking Clarifying Questions in Open-Domain Information-Seeking Conversations
 
Content Based Image Retrieval
Content Based Image RetrievalContent Based Image Retrieval
Content Based Image Retrieval
 
Efficient Neural Network Architecture for Image Classfication
Efficient Neural Network Architecture for Image ClassficationEfficient Neural Network Architecture for Image Classfication
Efficient Neural Network Architecture for Image Classfication
 
Retrieval of Monuments Images Through ACO Optimization Approach
Retrieval of Monuments Images Through ACO Optimization ApproachRetrieval of Monuments Images Through ACO Optimization Approach
Retrieval of Monuments Images Through ACO Optimization Approach
 
Eren_Golge_MS_Thesis_2014
Eren_Golge_MS_Thesis_2014Eren_Golge_MS_Thesis_2014
Eren_Golge_MS_Thesis_2014
 
Microsoft COCO: Common Objects in Context
Microsoft COCO: Common Objects in Context Microsoft COCO: Common Objects in Context
Microsoft COCO: Common Objects in Context
 
A Benchmark for Simulated Manipulation
A Benchmark for Simulated ManipulationA Benchmark for Simulated Manipulation
A Benchmark for Simulated Manipulation
 
Reduce Query Time Up to 60% with Selective Search
Reduce Query Time Up to 60% with Selective SearchReduce Query Time Up to 60% with Selective Search
Reduce Query Time Up to 60% with Selective Search
 
Tutorial inns2019 full
Tutorial inns2019 fullTutorial inns2019 full
Tutorial inns2019 full
 

Último

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
 
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure serviceWhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure servicePooja Nehwal
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024Rafal Los
 
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...gurkirankumar98700
 
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
 
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
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdfhans926745
 
Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Allon Mureinik
 
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024The Digital Insurer
 
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
 
The Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxThe Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxMalak Abu Hammad
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsEnterprise Knowledge
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Miguel Araújo
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024The Digital Insurer
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationSafe Software
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Drew Madelung
 
Developing An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of BrazilDeveloping An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of BrazilV3cube
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerThousandEyes
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Igalia
 

Último (20)

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
 
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure serviceWhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
 
The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024The 7 Things I Know About Cyber Security After 25 Years | April 2024
The 7 Things I Know About Cyber Security After 25 Years | April 2024
 
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...
 
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
 
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
 
[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf[2024]Digital Global Overview Report 2024 Meltwater.pdf
[2024]Digital Global Overview Report 2024 Meltwater.pdf
 
Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)
 
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024
 
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
 
The Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxThe Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptx
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
 
Developing An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of BrazilDeveloping An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of Brazil
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
 

A Survey about Object Retrieval

  • 1. The Duality of Object Retrieval:
 Unsupervised and Supervised Approaches TUAN NGUYEN ANH THE UNIVERSITY OF TOKYO
  • 2. Index •  Part 1: Basic Object Retrieval Ø Unsupervised approaches •  Part 2: State-of-the-art results •  Part 3: Future attempts Ø Duality & supervised approaches •  Conclusion 2
  • 3. Part 1: Basic Object Retrieval
  • 6. 6 Key words for images Similar images Source: https://www.google.com/imghp Related info
  • 7. 7
  • 8. Pinterest: Zoom-in Search 8 Source: https://www.pinterest.com/
  • 9. Overview of the system 9 Query Database Matching Features
  • 10. Features in object retrieval 10 Query Database Matching Features
  • 11. Local features •  SIFT [Lowe, 1999, 2004] •  HOG [Dalal & Triggs, 2005] 11
  • 12. Global and deep features •  GIST features [Oliva et al., 2001] Ø Describe the images by spectral information •  Deep features Ø Extracted from neural networks 12 [Krizhevsky et al., 2012]
  • 13. Aggregated Features •  BoF [Sivic et al., 2003] •  Hamming Embedding [Jégou et al., 2008] •  Fisher Vector [Perronnin et al., 2007] •  VLAD [Jégou et al., 2012] 13
  • 14. Bag of Features (BoF) •  Cluster local descriptors to build a dictionary. •  Compute the BoF vector as a histogram of visual words. 14 Images c2 c3 Dictionary Bag of Features [Sivic et al., 2003]
  • 15. Hamming Embedding •  Each local descriptors set of an image will be encoded by a binary signature. 15 [Jégou et al., 2008]
  • 16. Fisher Vector (FV) •  Cluster the local descriptors by GMM •  Fisher Kernel •  Fisher Vector 16 Images Local descriptors GMM Fisher Vector [Perronnin et al., 2007]
  • 17. VLAD •  Replace the GMM in FV by k-means clustering •  Approximate FV by 17 Images Local descriptors K-means VLAD Vector [Jégou et al., 2012]
  • 18. Overview of the system 18 Query Database Matching Features
  • 19. Distances and similarities •  Euclidean distances •  Hamming distances •  Inner product •  Approximated distances (ADC): Ø Distance between query vector and compressed database vector. Ø [Jégou et al., 2011] 19
  • 20. Nearest neighbor search 20 Query Database Matching, Nearest neighbor search Features
  • 21. Nearest neighbor search 21 Nearest neighbor
  • 22. Indexing and compressing data •  Coarse-to-fine strategy Ø Use quantization techniques to build an inverted file (IVF) 22 c1 1 3 c2 2 c3 4 5 6 id code m bytes c2 c3 Inverted File Compressed vectorFaster search Better memory footprint [Jégou et al., 2011]
  • 23. Quantization techniques •  Compress the data for better memory footprint •  Search accuracy is acceptable with appropriate parameters 23 Recall = 95% with 64 bits code [Jégou et al., 2011] 3 5 6 id code m bytes
  • 24. Feature processing •  Square rooting [Arandjelovic & Zisserman, 2012] •  L2-normalization [Jain et al., 2012] •  Centralization [Tolias et al., 2013] •  Down-weight highly populated cells in aggregation [Jégou et al., 2009] •  Whitening [Jégou et al., 2010] 24
  • 25. Image processing: re-ranking •  Estimate a transformation between the query region and each target image. •  Target images are re-ranked based on the discriminability of the spatially verified visual words. 25 mAP with BoF: 0.618→0.645 [Philbin et al., 2007] Dataset: Oxford Buildings Queries
  • 26. Image processing: query expansion 26 mAP with BoF: 0.645→0.696 [Chum et al., 2007] •  Requery after reconstructing the original query. •  The new query is constructed from verified query in the first time retrieval. Dataset: Oxford Buildings
  • 28. Nearest neighbor search •  Datasets: 1M~1B vectors with ground truth data Ø BIGANN dataset: http://corpus-texmex.irisa.fr/ •  Evaluation Ø recall@R = the proportion of queries with NN ranked in top-R results. 28 c1 1 3 c2 2 c3 4 5 6 id code m bytes c2 c3 Inverted File Compressed vector
  • 29. Quantization techniques •  Additive Quantization [Babenko et al., 2014] •  Approximate a vector by the sum of codewords. •  Learn codewords by an iterative optimization. •  Composite Quantization [Zhang et al., 2014] •  Minimize the orthogonality of the approximation. 29
  • 30. Indexing techniques •  Multi-indexing [Babenko et al., 2012, 2015] •  Performance in a dataset of one billion SIFT vectors Ø Memory: 12 GB Ø Search time: 2 ms/query Ø recall@100 = 70% 30
  • 31. Image search •  Datasets: Oxford building dataset [Philbin et al., 2007] •  Evaluation Ø mAP: Mean average precision for a set of queries is the mean of the average precision scores for each query. 31
  • 32. Selective Match Kernel •  [Tolias et al., 2013] •  Apply the power normalization to each VLAD component to improve the accuracy. •  Use hashing to reduce the memory footprint. •  mAP = 0.817 on Oxford5K dataset [Philbin et al., 2007] 32
  • 33. Neural Codes •  [Babenko et al., 2014] •  Attempt to use features that are extracted from neural network to object retrieval. •  Features are fine-tuned. •  mAP = 0.435 with fc6 features on Oxford5K dataset. 33
  • 34. Sum-pooled convolutional features •  [Babenko et al., 2015] •  Deep features are sum-pooled and Gaussian weighted to improve the accuracy. •  mAP = 0.657 on Oxford5K dataset. 34
  • 35. Summary of image retrieval results 35 •  Search framework with deep features in object retrieval still need to be improved. Method Feature Framework mAP ASMK [Tolias et al., 2013] SIFT VLAD 0.817 Neural codes [Babenko et al., 2014] Deep features - 0.435 SPoC [Babenko et al., 2015] Deep features SPoC 0.657
  • 36. Part 3: Future attempts
  • 37. Attempts on current topics •  Improve the features: Ø Feature fusion Ø Find new match kernels Ø Improve the system with deep features? •  Improve the distance metrics and NN search. 37
  • 38. Dual-process system 38 •  [Stanovich et al., 1999, 2004] Fast, high capacity, implicit knowledge and basic emotions only . Slow, limited capacity, explicit knowledge and complicated emotions.
  • 39. Supervised Object Retrieval? •  More than just apply the deep features into retrieval. •  Learning while searching? •  Learning with feedback? 39
  • 40. The Duality of Object Retrieval •  The collaboration between unsupervised learning and supervised learning in object retrieval. 40 [Stanovich et al., 1999, 2004]
  • 41. Conclusion •  Basic Object Retrieval Ø Features: SIFT, HOG, GIST, deep features Ø Distance metrics and NN search Ø Hamming Embedding and Aggregation Ø Pre-processing and post-processing •  State-of-the-art results •  Future attempts: Duality & Supervised & Unsupervised? 41
  • 42. Thank you for listening