Research map / Continual learning / Class-incremental
Learnability-Driven Knowledge Assimilation for Class-Incremental Semantic Segmentation
Xinyue Zhang, Xu Zou, Wanjia Luo, Yanjie Wang, Jiahuan Zhou, Sheng Zhong, Luxin Yan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add Progressive Margin Learning (Lseg-PML) (ablation) | baseline · Pascal VOC 15-1 | mIoU: 65.4 -> 77.2 | Improved |
| add Smooth Knowledge Distillation (LSKD) (ablation) | baseline + PML · Pascal VOC 15-1 | mIoU: 77.2 -> 79.5 | Improved |
| add Misclassification-Aware Decoupling (LMAD) (ablation) | baseline + PML + SKD · Pascal VOC 15-1 | mIoU: 79.5 -> 80.1 | Improved |
| use LMAD instead of standard contrastive learning (ablation) | LDKA · Pascal VOC 15-1 | mIoU: 78.5 -> 79.5 | Improved |
| add competition matrix to contrastive learning (ablation) | contrastive decoupling · Pascal VOC 15-1 | mIoU: 78.5 -> 78.8 | Improved |
| use LMAD instead of orthogonality constraints (ablation) | LDKA · Pascal VOC 15-1 | mIoU: 77.4 -> 79.5 | Improved |
| raise margin/sensitivity ratio from balanced 1.0 to 1.5 (ablation) | LDKA · Pascal VOC 15-1 | mIoU: 80.1 -> 79.1 | Hurt |
| lower margin/sensitivity ratio from 1.0 to 0.5 (ablation) | LDKA · Pascal VOC 15-1 | mIoU: 80.1 -> 79.8 | Hurt |
| add LSKD to reduce inter-class confusion among classes 16-20 (ablation) | LDKA · Pascal VOC 15-1 (confusion rate) | mIoU: decreases of 7.5, 0.9, 5.4, 7.0, 2.0, 2.6, 4.4, 2.3, 0.6, and 10.9 percentage points | Improved |
| LDKA versus MBS on ADE20K 100-5 | LDKA · ADE20K 100-5 | mIoU: 38.1 -> 40.1 | Improved |
| LDKA versus MBS on Pascal VOC 2-2 | LDKA · Pascal VOC 2-2 | mIoU: 72.6 -> 75.3 | Improved |
| LDKA versus MBS on Pascal VOC 10-1 | LDKA · Pascal VOC 10-1 | mIoU: 76.6 -> 76.7 | No clear effect |
Closest papers by meaning
- Decomposed Knowledge Distillation for Class-Incremental Semantic Segmentation (NeurIPS 2022 · similarity 0.91)
- Inherit With Distillation and Evolve With Contrast: Exploring Class Incremental Semantic Segmentation Without Exemplar Memory (TPAMI 2023 · similarity 0.91)
- Incrementer: Transformer for Class-Incremental Semantic Segmentation With Knowledge Distillation Focusing on Old Class (CVPR 2023 · similarity 0.91)
- Modeling the Background for Incremental Learning in Semantic Segmentation (CVPR 2020 · similarity 0.90)
- CoMBO: Conflict Mitigation via Branched Optimization for Class Incremental Segmentation (CVPR 2025 · similarity 0.89)
- Adaptive Prototype Replay for Class Incremental Semantic Segmentation (AAAI 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.
