Weighted Channel-Wise Decomposed Convolutional Neural Networks

Yao Lu, Guangming Lu, Yuanrong XuNeural Process. Lett 2019 · OpenReview

Abstract

Currently, block term decomposition is widely utilized to factorize regular convolutional kernels with several groups to decrease parameters. However, networks designed based on this method lack adequate information interactions from every group. Therefore, the Weighted Channel-wise Decomposed Convolutions (WCDC) are proposed in this paper, and the relevant networks can be called WCDC-Nets. The WCDC convolutional kernel employ the channel-wise decomposition to reduce the parameters and computational complexity to the bone. Furthermore, a tiny learnable weighted module is also utilized to dig up connections of the outputs from channel-wise convolutions in the WCDC kernel. The WCDC filter can be easily applied in many popular networks and can be trained end to end, resulting in a significant improvement of model’s flexibility. Experimental results on the benchmark datasets showed that WCDC-Nets can achieve better performances with much fewer parameters and flop pointing computations.
BibTeX
@inproceedings{lu2019weighted,
  author = {Yao Lu and Guangming Lu and Yuanrong Xu},
  title = {{Weighted Channel-Wise Decomposed Convolutional Neural Networks}},
  booktitle = {Neural Process. Lett},
  year = {2019},
  url = {https://openreview.net/forum?id=z9-vawEqzjW},
}

Loading related content...

Figure