Deep LAC: Deep Localization, Alignment and Classification for Fine-Grained Recognition

Di Lin, Xiaoyong Shen, Cewu Lu, Jiaya Jia

CVPR 2015

doi:10.1109/CVPR.2015.7298775 /cvpr/2015/lin2015cvpr-deep/

Abstract

We propose a fine-grained recognition system that incorporates part localization, alignment, and classification in one deep neural network. This is a nontrivial process, as the input to the classification module should be functions that enable back-propagation in constructing the solver. Our major contribution is to propose a valve linkage function(VLF) for back-propagation chaining and form our deep localization, alignment and classification (LAC) system. The VLF can adaptively compromise the errors of classification and alignment when training the LAC model. It in turn helps update localization. The performance on fine-grained object data bears out the effectiveness of our LAC system.

PDF CVPR Semantic Scholar

Cite

Text

Lin et al. "Deep LAC: Deep Localization, Alignment and Classification for Fine-Grained Recognition." Conference on Computer Vision and Pattern Recognition, 2015. doi:10.1109/CVPR.2015.7298775

Markdown

[Lin et al. "Deep LAC: Deep Localization, Alignment and Classification for Fine-Grained Recognition." Conference on Computer Vision and Pattern Recognition, 2015.](https://mlanthology.org/cvpr/2015/lin2015cvpr-deep/) doi:10.1109/CVPR.2015.7298775

BibTeX

@inproceedings{lin2015cvpr-deep,
  title     = {{Deep LAC: Deep Localization, Alignment and Classification for Fine-Grained Recognition}},
  author    = {Lin, Di and Shen, Xiaoyong and Lu, Cewu and Jia, Jiaya},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2015},
  doi       = {10.1109/CVPR.2015.7298775},
  url       = {https://mlanthology.org/cvpr/2015/lin2015cvpr-deep/}
}