Mining Discriminative Triplets of Patches for Fine-Grained Classification

Yaming Wang, Jonghyun Choi, Vlad Morariu, Larry S. Davis

CVPR 2016

doi:10.1109/CVPR.2016.131 /cvpr/2016/wang2016cvpr-mining/

Abstract

Fine-grained classification involves distinguishing between similar sub-categories based on subtle differences in highly localized regions; therefore, accurate localization of discriminative regions remains a major challenge. We describe a patch-based framework to address this problem. We introduce triplets of patches with geometric constraints to improve the accuracy of patch localization, and automatically mine discriminative geometrically-constrained triplets for classification. The resulting approach only requires object bounding boxes. Its effectiveness is demonstrated using four publicly available fine-grained datasets, on which it outperforms or obtains comparable results to the state-of-the-art in classification.

PDF CVPR Semantic Scholar

Cite

Text

Wang et al. "Mining Discriminative Triplets of Patches for Fine-Grained Classification." Conference on Computer Vision and Pattern Recognition, 2016. doi:10.1109/CVPR.2016.131

Markdown

[Wang et al. "Mining Discriminative Triplets of Patches for Fine-Grained Classification." Conference on Computer Vision and Pattern Recognition, 2016.](https://mlanthology.org/cvpr/2016/wang2016cvpr-mining/) doi:10.1109/CVPR.2016.131

BibTeX

@inproceedings{wang2016cvpr-mining,
  title     = {{Mining Discriminative Triplets of Patches for Fine-Grained Classification}},
  author    = {Wang, Yaming and Choi, Jonghyun and Morariu, Vlad and Davis, Larry S.},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2016},
  doi       = {10.1109/CVPR.2016.131},
  url       = {https://mlanthology.org/cvpr/2016/wang2016cvpr-mining/}
}