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

Di Lin, Xiaoyong Shen, Cewu Lu, Jiaya Jia; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 1666-1674

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.

Related Material


[pdf]
[bibtex]
@InProceedings{Lin_2015_CVPR,
author = {Lin, Di and Shen, Xiaoyong and Lu, Cewu and Jia, Jiaya},
title = {Deep LAC: Deep Localization, Alignment and Classification for Fine-Grained Recognition},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2015}
}