Research map / Continual learning / Class-incremental
Modeling the Background for Incremental Learning in Semantic Segmentation
Check 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 |
|---|---|---|---|
| Model background semantic shift in both cross-entropy and distillation losses | Proposed method · Pascal-VOC and ADE20K incremental segmentation scenarios | performance on old and new classes | Helped |
| Use the proposed background-aware method instead of standard incremental-learning baselines | Pascal-VOC and ADE20K incremental segmentation scenarios · Pascal-VOC and ADE20K | performance | Helped |
| Add the modified cross-entropy treatment of background (ablation) | Proposed method · Incremental semantic segmentation | performance | Helped |
| Add background-aware knowledge distillation (ablation) | Proposed method · Incremental semantic segmentation | performance | Helped |
| Add new-class weight initialization (ablation) | Proposed method · Incremental semantic segmentation | performance | Helped |
| Distill only over old foreground classes, without modeling the old background relation (ablation) | Proposed method · All evaluated scenarios | scores on old and new classes | Hurt |
Closest papers by meaning
- Incrementer: Transformer for Class-Incremental Semantic Segmentation With Knowledge Distillation Focusing on Old Class (CVPR 2023 · similarity 0.93)
- Deconfound Semantic Shift and Incompleteness in Incremental Few-shot Semantic Segmentation (AAAI 2025 · similarity 0.89)
- CoMBO: Conflict Mitigation via Branched Optimization for Class Incremental Segmentation (CVPR 2025 · similarity 0.88)
- Beyond Background Shift: Rethinking Instance Replay in Continual Semantic Segmentation (CVPR 2025 · similarity 0.88)
- Towards Continual Universal Segmentation (CVPR 2025 · similarity 0.88)
- Diffusion-Driven Two-Stage Active Learning for Low-Budget Semantic Segmentation (NeurIPS 2025 · similarity 0.87)
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.