Research map / Continual learning / Class-incremental
Federated Incremental Semantic Segmentation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use FBL instead of RCIL + FL | Federated incremental semantic segmentation · Pascal-VOC 2012, 15-1 overlapped | mIoU: 50.0 -> 56.6 | Helped |
| Use FBL instead of MiB + FL | Federated incremental semantic segmentation · Pascal-VOC 2012, 4-4 overlapped | mIoU: 33.0 -> 43.9 | Helped |
| Use FBL instead of RCIL + FL | Federated incremental semantic segmentation · Pascal-VOC 2012, 8-2 overlapped | mIoU: 33.7 -> 35.7 | Helped |
| Use FBL instead of RCIL + FL | Federated incremental semantic segmentation · ADE20k, 100-10 overlapped | mIoU: 26.4 -> 27.9 | Helped |
| Add adaptive class-balanced pseudo labeling using class-specific entropy thresholds (ablation) | FBL · Pascal-VOC 2012, 4-4 overlapped | mIoU: 40.0 -> 43.9 | Helped |
| Add adaptive class-balanced pseudo labeling using class-specific entropy thresholds (ablation) | FBL · Pascal-VOC 2012, 8-2 overlapped | mIoU: 26.7 -> 35.7 | Helped |
| Add forgetting-balanced semantic compensation loss (ablation) | FBL · Pascal-VOC 2012, 4-4 overlapped | mIoU: 40.0 -> 43.9 | Helped |
| Add forgetting-balanced semantic compensation loss (ablation) | FBL · Pascal-VOC 2012, 8-2 overlapped | mIoU: 29.2 -> 35.7 | Helped |
| Add forgetting-balanced relation consistency loss (ablation) | FBL · Pascal-VOC 2012, 4-4 overlapped | mIoU: 32.3 -> 43.9 | Helped |
| Add forgetting-balanced relation consistency loss (ablation) | FBL · Pascal-VOC 2012, 8-2 overlapped | mIoU: 28.7 -> 35.7 | Helped |
Closest papers by meaning
- Federated Class-Incremental Learning (CVPR 2022 · similarity 0.88)
- Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting (ICLR 2025 · similarity 0.87)
- Accurate Forgetting for Heterogeneous Federated Continual Learning (ICLR 2024 · similarity 0.86)
- TIKP: Text-to-Image Knowledge Preservation for Continual Semantic Segmentation (AAAI 2024 · similarity 0.86)
- Beyond Background Shift: Rethinking Instance Replay in Continual Semantic Segmentation (CVPR 2025 · similarity 0.85)
- Federated Black-Box Adaptation for Semantic Segmentation (NeurIPS 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.