Papers › SERNet-Former: Semantic Segmentation by Efficient Residual Network with...

SERNet-Former: Semantic Segmentation by Efficient Residual Network with Attention-Boosting Gates and Attention-Fusion Networks

28 Jan 2024arXiv:2401.15741archive 2025-07-28

Serdar Erisen

Improving the efficiency of state-of-the-art methods in semantic segmentation requires overcoming the increasing computational cost as well as issues such as fusing semantic information from global and local contexts. Based on the recent success and problems that convolutional neural networks (CNNs) encounter in semantic segmentation, this research proposes an encoder-decoder architecture with a unique efficient residual network, Efficient-ResNet. Attention-boosting gates (AbGs) and attention-boosting modules (AbMs) are deployed by aiming to fuse the equivariant and feature-based semantic information with the equivalent sizes of the output of global context of the efficient residual network in the encoder. Respectively, the decoder network is developed with the additional attention-fusion networks (AfNs) inspired by AbM. AfNs are designed to improve the efficiency in the one-to-one conversion of the semantic information by deploying additional convolution layers in the decoder part. Our network is tested on the challenging CamVid and Cityscapes datasets, and the proposed methods reveal significant improvements on the residual networks. To the best of our knowledge, the developed network, SERNet-Former, achieves state-of-the-art results (84.62 % mean IoU) on CamVid dataset and challenging results (87.35 % mean IoU) on Cityscapes validation dataset.

PaperPDFCode

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

Code

serdarch/sernet-former officialmentioned in paperpytorchNOASSERTION report
serdarch/SERNet-Former pytorchNOASSERTION 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

2D Semantic SegmentationDecoderSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
2D Semantic Segmentation CamVid SERNet-Former mIoU 84.62 #1 of 1 Archive leaderboard report
2D Semantic Segmentation Cityscapes val SERNet-Former mIoU 87.35 #1 of 1 Archive leaderboard report
Semantic Segmentation ADE20K SERNet-Former Validation mIoU 59.35 #17 of 235 Archive leaderboard report
Semantic Segmentation ADE20K val SERNet-Former_v2 mIoU 59.35 #8 of 95 Archive leaderboard report
Semantic Segmentation BDD100K val SERNet-Former_v2 mIoU 67.42 #2 of 24 Archive leaderboard report
Semantic Segmentation CamVid SERNet-Former Mean IoU 84.62 #1 of 21 Archive leaderboard report
Semantic Segmentation Cityscapes test SERNet-Former Mean IoU (class) 84.83 #7 of 105 Archive leaderboard report
Semantic Segmentation Cityscapes val SERNet-Former Validation mIoU 87.35 #2 of 99 Archive leaderboard report
Semantic Segmentation Cityscapes val SERNet-Former mIoU 87.35 #2 of 99 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

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingMulti-Attention NetworkPixelCNNReLUResidual BlockResidual Connection

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