DO-Conv: Depthwise Over-Parameterized Convolutional Layer - PubMed Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022:31:3726-3736.
doi: 10.1109/TIP.2022.3175432. Epub 2022 May 26.

DO-Conv: Depthwise Over-Parameterized Convolutional Layer

Jinming Cao, Yangyan Li, Mingchao Sun, Ying Chen, Dani Lischinski, Daniel Cohen-Or, Baoquan Chen, Changhe Tu

DO-Conv: Depthwise Over-Parameterized Convolutional Layer

Jinming Cao et al. IEEE Trans Image Process. 2022.

Abstract

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. The composition of the two convolutions constitutes an over-parameterization, since it adds learnable parameters, while the resulting linear operation can be expressed by a single convolution layer. We refer to this depthwise over-parameterized convolutional layer as DO-Conv, which is a novel way of over-parameterization. We show with extensive experiments that the mere replacement of conventional convolutional layers with DO-Conv layers boosts the performance of CNNs on many classical vision tasks, such as image classification, detection, and segmentation. Moreover, in the inference phase, the depthwise convolution is folded into the conventional convolution, reducing the computation to be exactly equivalent to that of a convolutional layer without over-parameterization. As DO-Conv introduces performance gains without incurring any computational complexity increase for inference, we advocate it as an alternative to the conventional convolutional layer. We open sourced an implementation of DO-Conv in Tensorflow, PyTorch and GluonCV at https://github.com/yangyanli/DO-Conv.

PubMed Disclaimer

Similar articles

See all similar articles

Cited by

See all "Cited by" articles