Discriminative Sparse Image Models for Class-Specific Edge Detection and Image Interpretation
Abstract
Sparse signal models learned from data are widely used in audio, image, and video restoration. They have recently been generalized to discriminative image understanding tasks such as texture segmentation and feature selection. This paper extends this line of research by proposing a multiscale method to minimize least-squares reconstruction errors and discriminative cost functions under ℓ_0 or ℓ_1 regularization constraints. It is applied to edge detection, category-based edge selection and image classification tasks. Experiments on the Berkeley edge detection benchmark and the PASCAL VOC’05 and VOC’07 datasets demonstrate the computational efficiency of our algorithm and its ability to learn local image descriptions that effectively support demanding computer vision tasks.
Cite
Text
Mairal et al. "Discriminative Sparse Image Models for Class-Specific Edge Detection and Image Interpretation." European Conference on Computer Vision, 2008. doi:10.1007/978-3-540-88690-7_4Markdown
[Mairal et al. "Discriminative Sparse Image Models for Class-Specific Edge Detection and Image Interpretation." European Conference on Computer Vision, 2008.](https://mlanthology.org/eccv/2008/mairal2008eccv-discriminative/) doi:10.1007/978-3-540-88690-7_4BibTeX
@inproceedings{mairal2008eccv-discriminative,
title = {{Discriminative Sparse Image Models for Class-Specific Edge Detection and Image Interpretation}},
author = {Mairal, Julien and Leordeanu, Marius and Bach, Francis R. and Hebert, Martial and Ponce, Jean},
booktitle = {European Conference on Computer Vision},
year = {2008},
pages = {43-56},
doi = {10.1007/978-3-540-88690-7_4},
url = {https://mlanthology.org/eccv/2008/mairal2008eccv-discriminative/}
}