2021/03/15 by Yunsheng Lou, Li, Yunsheng, Yinpeng Chen +14 · 1 citation
Computer Science · #Advanced Neural Network Applications #Adversarial Robustness in Machine Learning #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis
paper · pdf · doi:10.48550/arxiv.2103.08756
openalex created_date 2021/02/15 · openalex publication_date 2021/03/15 · openalex updated_date 2026/07/28
Recent research in dynamic convolution shows substantial performance boost for efficient CNNs, due to the adaptive aggregation of K static convolution kernels. It has two limitations: (a) it increases the number of convolutional weights by K-times, and (b) the joint optimization of dynamic attention and static convolution kernels is challenging. In this paper, we revisit it from a new perspective of matrix decomposition and reveal the key issue is that dynamic convolution applies dynamic attention over channel groups after projecting into a higher dimensional latent space. To address this issue, we propose dynamic channel fusion to replace dynamic attention over channel groups. Dynamic channel fusion not only enables significant dimension reduction of the latent space, but also mitigates the joint optimization difficulty. As a result, our method is easier to train and requires significantly fewer parameters without sacrificing accuracy. Source code is at https://github.com/liyunsheng13/dcd.