Diverse Branch Block: Building a Convolution as an Inception-like Unit

Xiaohan Ding, Xiangyu Zhang, Jungong Han, Guiguang Ding

Research output: Other contribution

127 Citations (SciVal)


We propose a universal building block of Convolutional Neural Network (ConvNet) to improve the performance without any inference-time costs. The block is named Diverse Branch Block (DBB), which enhances the representational capacity of a single convolution by combining diverse branches of different scales and complexities to enrich the feature space, including sequences of convolutions, multi-scale convolutions, and average pooling. After training, a DBB can be equivalently converted into a single conv layer for deployment. Unlike the advancements of novel ConvNet architectures, DBB complicates the training-time microstructure while maintaining the macro architecture, so that it can be used as a drop-in replacement for regular conv layers of any architecture. In this way, the model can be trained to reach a higher level of performance and then transformed into the original inference-time structure for inference. DBB improves ConvNets on image classification (up to 1.9% higher top-1 accuracy on ImageNet), object detection and semantic segmentation. The PyTorch code and models are released at https://github.com/DingXiaoH/DiverseBranchBlock.
Original languageEnglish
Number of pages10
Place of PublicationTsinghua Univ, Beijing Natl Res Ctr Informat Sci & Technol BNRis, Beijing, Peoples R China
ISBN (Electronic)9781665445092
Publication statusPublished - 2021

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (Print)1063-6919


Dive into the research topics of 'Diverse Branch Block: Building a Convolution as an Inception-like Unit'. Together they form a unique fingerprint.

Cite this