Papers › Sequential Ensembling for Semantic Segmentation
Sequential Ensembling for Semantic Segmentation
Rawal Khirodkar, Brandon Smith, Siddhartha Chandra, Amit Agrawal, Antonio Criminisi
Ensemble approaches for deep-learning-based semantic segmentation remain insufficiently explored despite the proliferation of competitive benchmarks and downstream applications. In this work, we explore and benchmark the popular ensembling approach of combining predictions of multiple, independently-trained, state-of-the-art models at test time on popular datasets. Furthermore, we propose a novel method inspired by boosting to sequentially ensemble networks that significantly outperforms the naive ensemble baseline. Our approach trains a cascade of models conditioned on class probabilities predicted by the previous model as an additional input. A key benefit of this approach is that it allows for dynamic computation offloading, which helps deploy models on mobile devices. Our proposed novel ADaptive modulatiON (ADON) block allows spatial feature modulation at various layers using previous-stage probabilities. Our approach does not require sophisticated sample selection strategies during training and works with multiple neural architectures. We significantly improve over the naive ensemble baseline on challenging datasets such as Cityscapes, ADE-20K, COCO-Stuff, and PASCAL-Context and set a new state-of-the-art.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
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 | Sequential Ensemble (SegFormer) | Params (M) | 216.3 | #70 of 235 | Archive leaderboard | report |
| Semantic Segmentation | ADE20K | Sequential Ensemble (SegFormer) | Validation mIoU | 54 | #70 of 235 | Archive leaderboard | report |
| Semantic Segmentation | ADE20K | Sequential Ensemble (DeepLabv3+) | Validation mIoU | 46.8 | #171 of 235 | Archive leaderboard | report |
| Semantic Segmentation | Cityscapes val | Sequential Ensemble (MiT-B5 + HRNet) | mIoU | 84.8 | #12 of 99 | Archive leaderboard | report |
| Semantic Segmentation | PASCAL Context | Sequential Ensemble (Segformer + HRNet) | mIoU | 62.1 | #11 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.
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