Research map / Detection and segmentation / Open-set and few-shot detection
Learning Semantic-Robust Change Detection via Semantic-Invariant Self-Distillation
Jiuhe Qu, Yingping Liang, Ying Fu
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 perturbation simulation to vanilla (ablation) | Change detector · SECOND | Fscd: 62.86 -> 63.55 | Improved |
| add semantic-invariant self-distillation to vanilla (ablation) | Change detector · SECOND | Fscd: 62.86 -> 63.91 | Improved |
| add both simulation and distillation (ablation) | Change detector · SECOND | Fscd: 62.86 -> 65.64 | Improved |
| add both simulation and distillation (ablation) | Change detector · SECOND | SeK: 22.30 -> 25.12 | Improved |
| add self-distillation on top of simulation (ablation) | Change detector · SECOND (1% labels) | Fscd: 51.8 -> 55.6 | Improved |
| add perturbation simulation on top of distillation (ablation) | Change detector · SECOND (1% labels) | Fscd: 48.9 -> 55.6 | Improved |
| add self-distillation on top of simulation (ablation) | Change detector · SECOND (1% labels) | SeK: 9.8 -> 15.0 | Improved |
| add self-distillation on top of simulation (ablation) | Change detector · SECOND (10% labels) | Fscd: 59.6 -> 62.5 | Improved |
| replace Change3D with SCDistill | Semantic CD · SECOND | SeK: 22.98 -> 25.12 | Improved |
| replace Change3D with SCDistill | Semantic CD · HRSCD | Fscd: 73.29 -> 74.29 | Improved |
| replace Change3D with SCDistill | Binary CD · CLCD | F1: 78.03 -> 78.97 | Improved |
| replace Change3D with SCDistill | Binary CD · LEVIR-CD | OA: 99.17 -> 99.16 | No clear effect |
Closest papers by meaning
- The Change You Want To Detect: Semantic Change Detection In Earth Observation With Hybrid Data Generationf (CVPR 2025 · similarity 0.88)
- FM-ChangeNet: Learning Change through Pathwise Feature Transport (NeurIPS 2026 · similarity 0.87)
- ChangeDiff: A Multi-Temporal Change Detection Data Generator with Flexible Text Prompts via Diffusion Model (AAAI 2025 · similarity 0.87)
- Segment Any Change (NeurIPS 2024 · similarity 0.86)
- Towards Generalizable Scene Change Detection (CVPR 2025 · similarity 0.86)
- Change3D: Revisiting Change Detection and Captioning from A Video Modeling Perspective (CVPR 2025 · similarity 0.86)
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.
