This paper addresses representational block named Hierarchical-Split Block, which can be taken as a plug-and-play block to upgrade existing convolutional neural networks, improves model performance significantly in a network. Hierarchical-Split Block contains many hierarchical split and concatenate connections within one single residual block. We find multi-scale features is of great importance for numerous vision tasks. Moreover, Hierarchical-Split block is very flexible and efficient, which provides a large space of potential network architectures for different applications. In this work, we present a common backbone based on Hierarchical-Split block for tasks: image classification, object detection, instance segmentation and semantic image segmentation/parsing. Our approach shows significant improvements over all these core tasks in comparison with the baseline. As shown in Figure1, for image classification, our 50-layers network(HS-ResNet50) achieves 81.28% top-1 accuracy with competitive latency on ImageNet-1k dataset. It also outperforms most state-of-the-art models. The source code and models will be available on: https://github.com/PaddlePaddle/PaddleClas
@article{arxiv.2010.07621,
title = {HS-ResNet: Hierarchical-Split Block on Convolutional Neural Network},
author = {Pengcheng Yuan and Shufei Lin and Cheng Cui and Yuning Du and Ruoyu Guo and Dongliang He and Errui Ding and Shumin Han},
journal= {arXiv preprint arXiv:2010.07621},
year = {2020}
}