# DO-Conv: Depthwise Over-parameterized Convolutional Layer

Source: [DO-Conv: Depthwise Over-parameterized Convolutional Layer](<https://www.sota2.com/research/paper/68fa67c61e209131cea183ba>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:43.264Z

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

Published: 2020-06-22T06:57:10.000Z

## 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. 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-source a reference implementation of DO-Conv in Tensorflow, PyTorch and GluonCV at https://github.com/yangyanli/DO-Conv.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2006.12030>)

[PDF](<https://arxiv.org/pdf/2006.12030.pdf>)
