Papers › SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation

SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation

18 Sep 2022arXiv:2209.08575archive 2025-07-28

Meng-Hao Guo, Cheng-Ze Lu, Qibin Hou, ZhengNing Liu, Ming-Ming Cheng, Shi-Min Hu

We present SegNeXt, a simple convolutional network architecture for semantic segmentation. Recent transformer-based models have dominated the field of semantic segmentation due to the efficiency of self-attention in encoding spatial information. In this paper, we show that convolutional attention is a more efficient and effective way to encode contextual information than the self-attention mechanism in transformers. By re-examining the characteristics owned by successful segmentation models, we discover several key components leading to the performance improvement of segmentation models. This motivates us to design a novel convolutional attention network that uses cheap convolutional operations. Without bells and whistles, our SegNeXt significantly improves the performance of previous state-of-the-art methods on popular benchmarks, including ADE20K, Cityscapes, COCO-Stuff, Pascal VOC, Pascal Context, and iSAID. Notably, SegNeXt outperforms EfficientNet-L2 w/ NAS-FPN and achieves 90.6% mIoU on the Pascal VOC 2012 test leaderboard using only 1/10 parameters of it. On average, SegNeXt achieves about 2.0% mIoU improvements compared to the state-of-the-art methods on the ADE20K datasets with the same or fewer computations. Code is available at https://github.com/uyzhang/JSeg (Jittor) and https://github.com/Visual-Attention-Network/SegNeXt (Pytorch).

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

visual-attention-network/segnext officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
open-mmlab/mmsegmentation mentioned in paperpytorchApache-2.0 report
open-edge-platform/geti mentioned on GitHubpytorchApache-2.0 report
Jittor/JSeg pytorchApache-2.0 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

Real-Time Semantic SegmentationSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Real-Time Semantic Segmentation Cityscapes val SegNext-T-Seg100 Frame (fps) 28.1 #4 of 24 Archive leaderboard report
Real-Time Semantic Segmentation Cityscapes val SegNext-T-Seg100 mIoU 79.8% #4 of 24 Archive leaderboard report
Semantic Segmentation DDD17 SegNeXt-B mIoU 71.46 #4 of 9 Archive leaderboard report
Semantic Segmentation DSEC SegNeXt-B mIoU 71.55 #5 of 9 Archive leaderboard report
Semantic Segmentation iSAID SegNeXt-L mIoU 70.3 #1 of 19 Archive leaderboard report
Semantic Segmentation iSAID SegNeXt-B mIoU 69.9 #2 of 19 Archive leaderboard report
Semantic Segmentation iSAID SegNeXt-S mIoU 68.8 #4 of 19 Archive leaderboard report
Semantic Segmentation iSAID SegNeXt-T mIoU 68.3 #6 of 19 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Average PoolingBatch NormalizationConvolutionGlobal Average PoolingNAS-FPNReLUTest

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