Papers › Efficient Self-Ensemble for Semantic Segmentation
Efficient Self-Ensemble for Semantic Segmentation
Walid Bousselham, Guillaume Thibault, Lucas Pagano, Archana Machireddy, Joe Gray, Young Hwan Chang, Xubo Song
Ensemble of predictions is known to perform better than individual predictions taken separately. However, for tasks that require heavy computational resources, e.g. semantic segmentation, creating an ensemble of learners that needs to be trained separately is hardly tractable. In this work, we propose to leverage the performance boost offered by ensemble methods to enhance the semantic segmentation, while avoiding the traditional heavy training cost of the ensemble. Our self-ensemble approach takes advantage of the multi-scale features set produced by feature pyramid network methods to feed independent decoders, thus creating an ensemble within a single model. Similar to the ensemble, the final prediction is the aggregation of the prediction made by each learner. In contrast to previous works, our model can be trained end-to-end, alleviating the traditional cumbersome multi-stage training of ensembles. Our self-ensemble approach outperforms the current state-of-the-art on the benchmark datasets Pascal Context and COCO-Stuff-10K for semantic segmentation and is competitive on ADE20K and Cityscapes. Code is publicly available at github.com/WalBouss/SenFormer.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
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 |
|---|---|---|---|---|---|---|---|
| Semantic Segmentation | ADE20K | SenFormer (BEiT-L) | Validation mIoU | 57.1 | #34 of 235 | Archive leaderboard | report |
| Semantic Segmentation | ADE20K | SenFormer (Swin-L) | Validation mIoU | 54.2 | #65 of 235 | Archive leaderboard | report |
| Semantic Segmentation | ADE20K val | SenFormer (BEiT-L) | mIoU | 57.1 | #21 of 95 | Archive leaderboard | report |
| Semantic Segmentation | ADE20K val | SenFormer (Swin-L) | mIoU | 54.2 | #35 of 95 | Archive leaderboard | report |
| Semantic Segmentation | COCO-Stuff test | SenFormer (Swin-L) | mIoU | 50.1% | #7 of 21 | Archive leaderboard | report |
| Semantic Segmentation | PASCAL Context | SenFormer (Swin-L) | mIoU | 64.0 | #10 of 66 | Archive leaderboard | report |
| Semantic Segmentation | PASCAL Context | SenFormer (ResNet-101) | mIoU | 56.6 | #22 of 66 | 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.
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