SOTAVerified

ResNeSt: Split-Attention Networks

2020-04-19Code Available3· sign in to hype

Hang Zhang, Chongruo wu, Zhongyue Zhang, Yi Zhu, Haibin Lin, Zhi Zhang, Yue Sun, Tong He, Jonas Mueller, R. Manmatha, Mu Li, Alexander Smola

arXivPDF

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

It is well known that featuremap attention and multi-path representation are important for visual recognition. In this paper, we present a modularized architecture, which applies the channel-wise attention on different network branches to leverage their success in capturing cross-feature interactions and learning diverse representations. Our design results in a simple and unified computation block, which can be parameterized using only a few variables. Our model, named ResNeSt, outperforms EfficientNet in accuracy and latency trade-off on image classification. In addition, ResNeSt has achieved superior transfer learning results on several public benchmarks serving as the backbone, and has been adopted by the winning entries of COCO-LVIS challenge. The source code for complete system and pretrained models are publicly available.

Tasks

image-classificationImage ClassificationInstance SegmentationObject DetectionPanoptic SegmentationSemantic SegmentationTransfer Learning

Benchmark Results

DatasetModelMetricClaimedVerifiedStatus
ImageNetResNeSt-269Top 1 Accuracy84.5—Unverified
ImageNetResNeSt-50-fastTop 1 Accuracy80.64—Unverified
ImageNetResNeSt-50Top 1 Accuracy81.13—Unverified
ImageNetResNeSt-101Top 1 Accuracy83—Unverified
ImageNetResNeSt-200Top 1 Accuracy83.9—Unverified

Reproductions