Research map / Label-efficient and robust learning / Test-time adaptation
DC-TTA: Divide-and-Conquer Framework for Test-Time Adaptation of Interactive Segmentation
Jihun Kim, Hoyong Kwon, Hyeokjun Kweon, Wooseong Jeong, Kuk-Jin Yoon
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 divide-and-conquer click partitioning (no TTA) (ablation) | SAM ViT-B · CAMO | NoC90: 10.45 -> 10.20 | Improved |
| add divide-and-conquer click partitioning (no TTA) (ablation) | SAM ViT-B · TRASHCAN | FR90: 52.29 -> 51.26 | Improved |
| add naive test-time adaptation (ablation) | SAM ViT-B · TRASHCAN | FR90: 52.29 -> 43.18 | Improved |
| add divide strategy on top of TTA (ablation) | naive TTA SAM · CAMO | NoC90: 10.03 -> 9.83 | Improved |
| add divide strategy on top of TTA (ablation) | naive TTA SAM · TRASHCAN | FR90: 43.18 -> 39.67 | Improved |
| add model merging via task vectors (ablation) | DC-TTA without merging · CAMO | FR90: 27.20 -> 25.60 | Improved |
| add model merging via task vectors (ablation) | DC-TTA without merging · TRASHCAN | NoC90: 12.29 -> 12.05 | Improved |
| add DC-TTA over AdaptSAM | SAM ViT-B · TRASHCAN | FR90: 49.33 -> 38.80 | Improved |
| add DC-TTA | RITM · CAMO | NoC90: 10.51 -> 9.83 | Improved |
| add DC-TTA | FocalClick · TRASHCAN | FR90: 33.94 -> 26.37 | Improved |
| add DC-TTA | MFP · ISTD | FR90: 7.11 -> 6.74 | Improved |
| add DC-TTA | FocalClick · CAMO | FR90: 13.20 -> 13.20 | No clear effect |
Closest papers by meaning
- TETRIS: Towards Exploring the Robustness of Interactive Segmentation (AAAI 2024 · similarity 0.88)
- NTClick: Achieving Precise Interactive Segmentation With Noise-tolerant Clicks (CVPR 2025 · similarity 0.88)
- RClicks: Realistic Click Simulation for Benchmarking Interactive Segmentation (NeurIPS 2024 · similarity 0.88)
- SAM-REF: Introducing Image-Prompt Synergy during Interaction for Detail Enhancement in the Segment Anything Model (CVPR 2025 · similarity 0.87)
- Test-Time Adaptation of Vision-Language Models for Open-Vocabulary Semantic Segmentation (NeurIPS 2025 · similarity 0.87)
- FocSAM: Delving Deeply into Focused Objects in Segmenting Anything (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.
