DO-Conv: Depthwise Over-Parameterized Convolutional Layer

By Jinming Cao, Yangyan Li, Mingchao Sun, Ying Chen, Dani Lischinski, Daniel Cohen-Or, Baoquan Chen, Changhe Tu. 2020

251 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Model Architectures

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Model Architectures

Citations in the corpus

Initialization and Regularization of Factorized Neural Layers (2021, methodology): “On the other hand, if training cost is not a concern, one can increase the width or depth of the factors to over-parameterize models (Guo et al., 2020; Cao et al., 2020), improving learning without increasing inference-time cost.”
U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation (2024, methodology): “Followed each KAN layers, the features are passed through a efficient depth-wise convolutional layer (DwConv) [8] and a bacth normalization layer (BN) and a ReLU activation.”
RepVGG: Making VGG-style ConvNets Great Again (2021, background): “Asym Conv Block (ACB) [10], DO-Conv [1] and ExpandNet [11] can also be viewed as structural reparameterization in the sense that they convert a block into a conv.”
Diverse Branch Block: Building a Convolution as an Inception-like Unit (2021, background): “ExpandNet [10], DO-Conv [1] and ACNet [8] can also be categorized into structural re-parameterization in the sense that they convert a block into a conv.”