Presentation is loading. Please wait.

Presentation is loading. Please wait.

Online Dictionary Learning for Sparse Coding International Conference on Machine Learning, 2009 Julien Mairal, Francis Bach, Jean Ponce and Guillermo Sapiro.

Similar presentations


Presentation on theme: "Online Dictionary Learning for Sparse Coding International Conference on Machine Learning, 2009 Julien Mairal, Francis Bach, Jean Ponce and Guillermo Sapiro."— Presentation transcript:

1 Online Dictionary Learning for Sparse Coding International Conference on Machine Learning, 2009 Julien Mairal, Francis Bach, Jean Ponce and Guillermo Sapiro

2 Overview Introduction Problem Statement Online Dictionary Learning Experimental Validation Conclusion

3 Introduction The linear decomposition of a signal using a few atoms of a learned dictionary has recently led to state-of-the-art results for image processing tasks. While learning the dictionary has proven to be critical to achieve results, effectively solving the corresponding optimization problem is a significant computational challenge. (There may include millions of training sets.)

4 Introduction

5 Overview Introduction Problem Statement Online Dictionary Learning Experimental Validation Conclusion

6 Problem Statement

7

8 A nature approach to solving this problem is to alternate between the two variables, minimizing over one while keeping the other one fixed. In the case of dictionary learning, classical projected first-order stochastic gradient descent consists of a sequence of updates of D: The dictionary learning method authors present falls into the class of online algorithms based on stochastic approximations, processing one sample at a time, but exploits the specific structure of the problem to efficient solve it.

9 Overview Introduction Problem Statement Online Dictionary Learning Experimental Validation Conclusion

10 Online Dictionary Learning-Algorithm Outline

11 Online Dictionary Learning – Sparse Coding The sparse coding problem of Eq. (2) with fixed dictionary is an L1- regularized linear least-squares problem. The columns of learned dictionaries are in general highly correlated, so authors use LARS-Lasso algorithm (Osborne et al., 2000; Efron et al., 2004) to provide whole regularization path (i.e. for all possible values of λ).

12

13

14 Online Dictionary Learning – Dictionary Update

15 Overview Introduction Problem Statement Online Dictionary Learning Experimental Validation Conclusion

16 Experimental Validation

17 Overview Introduction Problem Statement Online Dictionary Learning Experimental Validation Conclusion

18 Authors have introduced in this paper a new stochastic online algorithm for learning dictionaries adapted to sparse coding tasks. Preliminary experiments demonstrate that it is significantly faster than batch alternatives on large datasets that may contain millions of training example.

19 An Efficient Frame-Content Based Intra Frame Rate Control for HEVC IEEE SIGNAL PROCESSING LETTERS, VOL. 22, NO 7, JULY 2015 Miaohui Wang, King Ngi Ngan, and Hongliang Li

20 Overview Introduction Proposed Rate Control Method Simulation Results Conclusion

21 Introduction In this letter, authors propose a new gradient based R-λ model for the HEVC intra frame rate control, where the gradient is used to measure the frame-content complexity. In addition, a novel bit allocation method is developed for CTU rate control.

22 Overview Introduction Proposed Rate Control Method Simulation Results Conclusion

23 Modeling the Relationship Between Rate-Gradient and λ for the HEVC Frame Coding Due to that different frames have different encoding complexities, the frame-content complexity measure is incorporated into the proposed method for HEVC intra frame coding.

24 Bit Allocation – GOP Level Bit Allocation Original – GOP LevelProposed – GOP Level Original – Frame LevelProposed – Frame Level Original – CU LevelProposed – CU Level

25 Model Parameter Update Original Proposed

26 Overview Introduction Proposed Rate Control Method Simulation Results Conclusion

27 Simulation Configuration 1.HM 10.0 : the original HM 10.0 without rate control 2.JCT-VC K0103: the original HM 10.0 with the default rate control 3.JCT-VC M0257: the original HM 10.0 with the default intra frame rate control 4.Proposed method

28 Simulation Results

29

30 Overview Introduction Proposed Rate Control Method Simulation Results Conclusion

31 In this letter, a frame-content based rate control method is proposed for the HEVC intra frame coding. The frame-content complexity is measured by its gradient, which has been incorporated into an improved R-λ model. A new bit allocation scheme with content complexity is developed at the CTU level.


Download ppt "Online Dictionary Learning for Sparse Coding International Conference on Machine Learning, 2009 Julien Mairal, Francis Bach, Jean Ponce and Guillermo Sapiro."

Similar presentations


Ads by Google