1 / 20

Locality-constrained Linear Coding for Image Classification

Locality-constrained Linear Coding for Image Classification. Presenter : Han-Mu Park. Locality-constrained Linear Coding for Image Classification, CVPR 2010. Contents. Introduction Coding methods Proposed method Experimental results Conclusion References.

kennan
Download Presentation

Locality-constrained Linear Coding for Image Classification

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Locality-constrained Linear Coding for Image Classification Presenter : Han-Mu Park

  2. Locality-constrained Linear Coding for Image Classification, CVPR 2010 Contents • Introduction • Coding methods • Proposed method • Experimental results • Conclusion • References

  3. Locality-constrained Linear Coding for Image Classification, CVPR 2010 Introduction • Bag-of-Words (BoW) model • An image is represented as a collection of visual words. • Generally, to represent the collection, histogram of words form is used.

  4. Locality-constrained Linear Coding for Image Classification, CVPR 2010 Introduction • General Spatial Pyramid Matching frameworks • Feature extraction • SIFT • HOG • etc • Coding • Vector Quantization • Sparse coding • etc • Pooling • Max pooling • Sum pooling Spatial Pyramid Matching framework [J.Wang2010]

  5. Locality-constrained Linear Coding for Image Classification, CVPR 2010 Introduction • General Spatial Pyramid Matching frameworks Spatial Pyramid Matching framework [J.Wang2010]

  6. Locality-constrained Linear Coding for Image Classification, CVPR 2010 Coding methods • Coding methods • Vector quantization (VQ) • Sparce coding (SC) • Locality-constrained Linear Coding (LLC) [J.Wang2010]

  7. Locality-constrained Linear Coding for Image Classification, CVPR 2010 Coding methods • Vector quantization (VQ) • Hard quantization method • A set of -dimensional local descriptors • Codebook with entries • Objective function • Where is the set of codes for X

  8. Locality-constrained Linear Coding for Image Classification, CVPR 2010 Coding methods • Sparse coding (SC) • Soft quantization method • Relaxed the cardinality constraint • Objective function • The roles of sparsity regularization term • Because the codebook is usually over-complete , it is necessary to ensure that the under-determined system has a unique solution. • Sparsity allows the learned representation to capture salient patterns of local descriptors. • The sparse coding can achieve much less quantization error than VQ.

  9. Locality-constrained Linear Coding for Image Classification, CVPR 2010 Proposed method • Locality-constrained Linear Coding (LLC) • Replaced the sparsity regularization term with new constraint. • Objective function • : the element-wise multiplication Where

  10. Locality-constrained Linear Coding for Image Classification, CVPR 2010 Proposed method • Properties of LLC • Better reconstruction • Because LLC represents each descriptor by using multiple weighted bases (codewords), it has less reconstruction error than VQ. • Local smooth sparsity • Because the regularization term of in SC is not smooth, therefore, SC loses correlations between codes. • Analytical solution • The solution of LLC can be derived analytically by Where

  11. Locality-constrained Linear Coding for Image Classification, CVPR 2010 Proposed method • Approximated LLC for fast encoding • The LLC selects the local bases for each descriptor to form a local coordinate system. • To speedup the encoding process, authors used nearest neighbors of as the local bases , and solve a much smaller linear system to get the codes • The reduced computation complexity • , where

  12. Locality-constrained Linear Coding for Image Classification, CVPR 2010 Proposed method • Codebook optimization • To improve the accuracy, authors trained the codebook to optimize for LLC codes. • The optimal codebook can be obtained by • This can be solved by using Coordinate Descent method. • However, because the number of training descriptors is usually very large, the huge memory space is needed to solve that problem.

  13. Locality-constrained Linear Coding for Image Classification, CVPR 2010 Proposed method • Incremental codebook optimization • First, initialize by using K-means clustering. • Then loop through all the training descriptors to update incrementally. • In each iteration, we take in a single (or a small set of) examples , and solve original objective function to obtain the corresponding LLC codes. [J.Wang2010]

  14. Locality-constrained Linear Coding for Image Classification, CVPR 2010 Proposed method • Incremental codebook optimization • Then select bases whose corresponding weights are larger than predefined threshold, and refit without the locality constraint. • The obtained code is used to update the basis in a gradient descent fashion. [J.Wang2010]

  15. Locality-constrained Linear Coding for Image Classification, CVPR 2010 Experimental results • Performance of codebook

  16. Locality-constrained Linear Coding for Image Classification, CVPR 2010 Experimental results • Performance under different neighbors

  17. Locality-constrained Linear Coding for Image Classification, CVPR 2010 Experimental results • Results using Pascal VOC 2007

  18. Locality-constrained Linear Coding for Image Classification, CVPR 2010 Conclusion • Contribution • In this paper, the Locality-constrained Linear Coding (LCC) method is proposed • Better reconstruction • Local smooth sparsity • Analytical solution • For speedup, K-nearest neighbors algorithm is used. • To optimize the accuracy, incremental codebook learning is proposed for LCC.

  19. Locality-constrained Linear Coding for Image Classification, CVPR 2010 References [1] J. Wang, J. Yang, K. Yu, F. Lv, T. Huang, Y. Gong, “Locality-constrained Linear Coding for Image Classification,” CVPR 2010.

  20. Thank you!

More Related