Research map / Detection and segmentation / Open-set and few-shot detection
Segment and Matte Anything in a Unified Model
Zezhong Fan, Xiaohan Li, Topojoy Biswas, Kaushiki Nag, Kannan Achan
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 MVLE (ablation) | SAMA (with Local-Adapter) · DIS-VD | max F-measure: 0.893 -> 0.942 | Improved |
| add Local-Adapter (ablation) | SAMA (with MVLE) · DIS-VD | max F-measure: 0.882 -> 0.942 | Improved |
| add MVLE and Local-Adapter (ablation) | SAM baseline head · DIS-VD | max F-measure: 0.872 -> 0.942 | Improved |
| add MVLE and Local-Adapter (ablation) | SAMA · AM2K | SAD: 19.79 -> 8.04 | Improved |
| add matting task to joint training (ablation) | SAMA · DIS-VD | max F-measure: 0.917 -> 0.942 | Improved |
| add segmentation task to joint training (ablation) | SAMA · RefMatte-RW100 | SAD: 34.25 -> 25.69 | Improved |
| compare SAMA to BiRefNet on DIS-TE3 MAE | SAMA · DIS-TE3 | MAE: 0.028 vs 0.032 | Hurt |
| compare SAMA to trimap-based VITMatte on Composition-1K SAD | SAMA · Composition-1K | SAD: 21.5 vs 22.8 | No clear effect |
Closest papers by meaning
- FocSAM: Delving Deeply into Focused Objects in Segmenting Anything (CVPR 2024 · similarity 0.89)
- Segment Anything without Supervision (NeurIPS 2024 · similarity 0.88)
- AoP-SAM: Automation of Prompts for Efficient Segmentation (AAAI 2025 · similarity 0.88)
- SAM-REF: Introducing Image-Prompt Synergy during Interaction for Detail Enhancement in the Segment Anything Model (CVPR 2025 · similarity 0.88)
- Bridge the Points: Graph-based Few-shot Segment Anything Semantically (NeurIPS 2024 · similarity 0.88)
- SAM 2: Segment Anything in Images and Videos (ICLR 2025 · similarity 0.88)
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.
