Papers › HS-ResNet: Hierarchical-Split Block on Convolutional Neural Network

HS-ResNet: Hierarchical-Split Block on Convolutional Neural Network

15 Oct 2020arXiv:2010.07621archive 2025-07-28

Pengcheng Yuan, Shufei Lin, Cheng Cui, Yuning Du, Ruoyu Guo, Dongliang He, Errui Ding, Shumin Han

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

Paper PDF Code

Code

PaddlePaddle/PaddleClas officialmentioned in papermentioned on GitHubpaddleApache-2.0 report

murufeng/awesome_lightweight_networks pytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image Classification Image Segmentation Instance Segmentation Object Detection Segmentation Semantic Segmentation image-classification object-detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: HS-ResNet, Hierarchical-Split Block

1x1 Convolution Average Pooling Batch Normalization Convolution Dense Connections Depthwise Convolution Depthwise Separable Convolution Ghost Bottleneck Ghost Module GhostNet Global Average Pooling HS-ResNet Hierarchical-Split Block Pointwise Convolution ReLU Residual Connection Sigmoid Activation Softmax Squeeze-and-Excitation Block

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections