Unified Sparse Coding Framework (USCF)
Introduction
Sparse Coding is recently employed in many research areas of Image processing such as classification, transfer learning, cross-modalities, and hashing techniques.
One powerful toolbox, SPAMS [1], implemented different algorithms of DL and SC, however, many advanced algorithms such as Graph Sparse Coding [2] and Transfer Sparse Coding [3] have not implemented yet.
Former students of Machine Learning course implemented successfully the module of cross-modality learning in this framework. Further, they improved the performance of some implemented algorithms.
In this course, we are interested in implementing Transfer Sparse Coding algorithms as well as Feature Learning algorithms, in particular, [4].
Project Phases
| Phase | Period | Conducted by | Materials | Results so far |
|---|
| Sparse Coding and Dictionary Learning | April | all | Slides I
Slides II | |
What you are going to learn:
- Sparse Coding and Dictionary Learning
- ...
Programming Language
Useful Links
References
- [1] J. Mairal et.al. Sparse Modeling for Image and Vision Processing. Foundations and Trends in Computer Graphics and Vision. Vol 8. No. 2-3. Pp. 85--283. 2014
- [2] Zheng et.al., "Graph Regularized Sparse Coding for Image Representation," Image Processing, IEEE Transactions on. Vol.20. No.5. Pp.1327-1336, 2011
- [3] Long; et.al. "Transfer Sparse Coding for Robust Image Representation," Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on, pp.407-414, 23-28 June 2013
- [4] Kiro. Et. Al, “Stacked Multiscale Feature Learning for Domain Independent Medical Image Segmentation”, Machine Learning in Medical Imaging, 2014.
- [5] M. Fowler, Refactoring: Improving the Design of Existing Code.