ResNeSt: Split-Attention Networks

by   Hang Zhang, et al.

While image classification models have recently continued to advance, most downstream applications such as object detection and semantic segmentation still employ ResNet variants as the backbone network due to their simple and modular structure. We present a simple and modular Split-Attention block that enables attention across feature-map groups. By stacking these Split-Attention blocks ResNet-style, we obtain a new ResNet variant which we call ResNeSt. Our network preserves the overall ResNet structure to be used in downstream tasks straightforwardly without introducing additional computational costs. ResNeSt models outperform other networks with similar model complexities. For example, ResNeSt-50 achieves 81.13 of 224x224, outperforming previous best ResNet variant by more than 1 accuracy. This improvement also helps downstream tasks including object detection, instance segmentation and semantic segmentation. For example, by simply replace the ResNet-50 backbone with ResNeSt-50, we improve the mAP of Faster-RCNN on MS-COCO from 39.3 from 42.1


page 1

page 2

page 3

page 4


EPSANet: An Efficient Pyramid Split Attention Block on Convolutional Neural Network

Recently, it has been demonstrated that the performance of a deep convol...

Bottleneck Transformers for Visual Recognition

We present BoTNet, a conceptually simple yet powerful backbone architect...

Efficient Scale-Permuted Backbone with Learned Resource Distribution

Recently, SpineNet has demonstrated promising results on object detectio...

Does Robustness on ImageNet Transfer to Downstream Tasks?

As clean ImageNet accuracy nears its ceiling, the research community is ...

Optimal Correction Cost for Object Detection Evaluation

Mean Average Precision (mAP) is the primary evaluation measure for objec...

Could Giant Pretrained Image Models Extract Universal Representations?

Frozen pretrained models have become a viable alternative to the pretrai...

Panoptic SegFormer

We present Panoptic SegFormer, a general framework for end-to-end panopt...

Code Repositories


ResNeSt: Split-Attention Networks

view repo


ResNeSt: Split-Attention Networks for Tensorflow2

view repo


PyTorch implementation of ResNeSt : Split-Attention Networks

view repo


This repository houses the code for a streamlit powered web app (capable of running on an AWS `t2.micro` EC2 instance) backed with a CNN fine-tuned on the SIIM ISIC Melanoma Classification Competition data.

view repo

Please sign up or login with your details

Forgot password? Click here to reset