Research map / Continual learning / Class-incremental
Class Similarity Weighted Knowledge Distillation for Continual 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 |
|---|---|---|---|
| Use class-similarity-weighted knowledge distillation instead of normal knowledge distillation (ablation) | REMINDER · Pascal-VOC 2012 15-1 | all mIoU (%): 23.69 -> 58.52 | Helped |
| Use class-similarity-weighted knowledge distillation instead of UNKD (ablation) | REMINDER · Pascal-VOC 2012 15-1 | all mIoU (%): 50.29 -> 58.52 | Helped |
| Add CSW-KD to the output-distillation objective (ablation) | REMINDER · Pascal-VOC 2012 15-1 | avg mIoU (%): 62.47 -> 68.27 | Helped |
| Use REMINDER rather than PLOP | continual semantic segmentation · Pascal-VOC 2012 15-1 | all mIoU (%): 54.68 -> 58.52 | Helped |
| Use REMINDER rather than PLOP | continual semantic segmentation · Pascal-VOC 2012 15-1 | new-class mIoU (%): 26.76 -> 27.23 | Helped |
| Use REMINDER rather than PLOP | continual semantic segmentation · ADE20k 100-10 | all mIoU (%): 30.52 -> 33.11 | Helped |
| Use REMINDER rather than PLOP | continual semantic segmentation · ADE20k 100-10 | avg mIoU (%): 34.48 -> 37.47 | Helped |
| Use REMINDER rather than PLOP | continual semantic segmentation · ADE20k 50-50 | all mIoU (%): 29.41 -> 29.39 | No clear effect |
Closest papers by meaning
- Beyond Background Shift: Rethinking Instance Replay in Continual Semantic Segmentation (CVPR 2025 · similarity 0.91)
- TIKP: Text-to-Image Knowledge Preservation for Continual Semantic Segmentation (AAAI 2024 · similarity 0.89)
- Adaptive Prototype Replay for Class Incremental Semantic Segmentation (AAAI 2025 · similarity 0.88)
- Continual Segmentation with Disentangled Objectness Learning and Class Recognition (CVPR 2024 · similarity 0.88)
- Attacks on Continual Semantic Segmentation by Perturbing Incremental Samples (AAAI 2024 · similarity 0.88)
- Enhancing Visual Continual Learning with Language-Guided Supervision (CVPR 2024 · 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.