Papers › ShelfNet for Fast Semantic Segmentation
ShelfNet for Fast Semantic Segmentation
Juntang Zhuang, Junlin Yang, Lin Gu, Nicha Dvornek
In this paper, we present ShelfNet, a novel architecture for accurate fast semantic segmentation. Different from the single encoder-decoder structure, ShelfNet has multiple encoder-decoder branch pairs with skip connections at each spatial level, which looks like a shelf with multiple columns. The shelf-shaped structure can be viewed as an ensemble of multiple deep and shallow paths, thus improving accuracy. We significantly reduce computation burden by reducing channel number, at the same time achieving high accuracy with this unique structure. In addition, we propose a shared-weight strategy in the residual block which reduces parameter number without sacrificing performance. Compared with popular non real-time methods such as PSPNet, our ShelfNet achieves 4× faster inference speed with similar accuracy on PASCAL VOC dataset. Compared with real-time segmentation models such as BiSeNet, our model achieves higher accuracy at comparable speed on the Cityscapes Dataset, enabling the application in speed-demanding tasks such as street-scene understanding for autonomous driving. Furthermore, our ShelfNet achieves 79.0\% mIoU on Cityscapes Dataset with ResNet34 backbone, outperforming PSPNet and BiSeNet with large backbones such as ResNet101. Through extensive experiments, we validated the superior performance of ShelfNet. We provide link to the implementation \url{https://github.com/juntang-zhuang/ShelfNet-lw-cityscapes}.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Real-Time Semantic Segmentation | Cityscapes test | ShelfNet18 | Frame (fps) | 59.2 | #17 of 39 | Archive leaderboard | report |
| Real-Time Semantic Segmentation | Cityscapes test | ShelfNet18 | Time (ms) | 16.9 | #17 of 39 | Archive leaderboard | report |
| Real-Time Semantic Segmentation | Cityscapes test | ShelfNet18 | mIoU | 74.8% | #17 of 39 | Archive leaderboard | report |
| Semantic Segmentation | Cityscapes test | ShelfNet-34 | Mean IoU (class) | 79.0% | #57 of 105 | Archive leaderboard | report |
| Semantic Segmentation | PASCAL VOC 2012 test | ShelfNet | Mean IoU | 84.2% | #15 of 51 | 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
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