Deep Micro-Dictionary Learning and Coding Network

Hao Tang1 Heng Wei2 Wei Xiao3 Wei Wang4 Dan Xu5 Yan Yan6 Nicu Sebe1
1University of Trento, 2Hong Kong Polytechnic University, 3Lingxi Artificial Intelligence Co., Ltd
4EPFL, 5University of Oxford, 6Texas State University

In WACV 2019 (Oral)


[Paper][Code]

In this paper, we propose a novel Deep Micro-Dictionary Learning and Coding Network (DDLCN). DDLCN has most of the standard deep learning layers (pooling, fully, connected, input/output, etc.) but the main difference is that the fundamental convolutional layers are replaced by novel compound dictionary learning and coding layers. The dictionary learning layer learns an over-complete dictionary for the input training data. At the deep coding layer, a locality constraint is added to guarantee that the activated dictionary bases are close to each other. Next, the activated dictionary atoms are assembled together and passed to the next compound dictionary learning and coding layers. In this way, the activated atoms in the first layer can be represented by the deeper atoms in the second dictionary. Intuitively, the second dictionary is designed to learn the fine-grained components which are shared among the input dictionary atoms. In this way, a more informative and discriminative low-level representation of the dictionary atoms can be obtained. We empirically compare the proposed DDLCN with several dictionary learning methods and deep learning architectures. The experimental results on four popular benchmark datasets demonstrate that the proposed DDLCN achieves competitive results compared with state-of-the-art approaches.


Reference

Hao Tang, Heng Wei, Wei Xiao, Wei Wang, Dan Xu, Yan Yan, Nicu Sebe. Deep Micro-Dictionary Learning and Coding Network. In WACV 2019.

@inproceedings{tang2019deep,
  title={Deep Micro-Dictionary Learning and Coding Network},
  author={Tang, Hao and Wei, Heng and Xiao, Wei and Wang, Wei and Xu, Dan and Yan, Yan and Sebe, Nicu},
  booktitle={2019 IEEE Winter Conference on Applications of Computer Vision (WACV)},
  pages={386--395},
  year={2019},
  organization={IEEE}
}