DO-Conv: Depthwise Over-parameterized Convolutional Layer

22 Jun 2020Jinming CaoYangyan LiMingchao SunYing ChenDani LischinskiDaniel Cohen-OrBaoquan ChenChanghe Tu

Convolutional layers are the core building blocks of Convolutional Neural Networks (CNNs). In this paper, we propose to augment a convolutional layer with an additional depthwise convolution, where each input channel is convolved with a different 2D kernel... (read more)

PDF Abstract

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods used in the Paper