ML Anthology

Learning Non-Negative Sparse Image Codes by Convex Programming

Matthias Heiler, Christoph Schnörr
ICCV 2005 pp. 1667-1674
doi:10.1109/ICCV.2005.141 /iccv/2005/heiler2005iccv-learning/

Abstract

Example-based learning of codes that statistically encode general image classes is of vital importance for computational vision. Recently non negative matrix factorization (NMF) was suggested to provide image code that was both sparse and localized, in contrast to established non local methods like PCA. In this paper, we adopt and generalize this approach to develop a novel learning framework that allows to efficiently compute sparsity-controlled invariant image codes by a well defined sequence of convex conic programs. Applying the corresponding parameter-free algorithm to various image classes results in semantically relevant and transformation-invariant image representations that are remarkably robust against noise and quantization

ICCV Semantic Scholar

Cite

Text

Heiler and Schnörr. "Learning Non-Negative Sparse Image Codes by Convex Programming." IEEE/CVF International Conference on Computer Vision, 2005. doi:10.1109/ICCV.2005.141

Markdown

[Heiler and Schnörr. "Learning Non-Negative Sparse Image Codes by Convex Programming." IEEE/CVF International Conference on Computer Vision, 2005.](https://mlanthology.org/iccv/2005/heiler2005iccv-learning/) doi:10.1109/ICCV.2005.141

BibTeX

@inproceedings{heiler2005iccv-learning,
  title     = {{Learning Non-Negative Sparse Image Codes by Convex Programming}},
  author    = {Heiler, Matthias and Schnörr, Christoph},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2005},
  pages     = {1667-1674},
  doi       = {10.1109/ICCV.2005.141},
  url       = {https://mlanthology.org/iccv/2005/heiler2005iccv-learning/}
}