Research map / Detection and segmentation / Open-set and few-shot detection
Understanding Personal Concept in Open-Vocabulary Semantic Segmentation
Sunghyun Park, Jungsoo Lee, Shubhankar Borse, Munawar Hayat, Sungha Choi, Kyuwoong Hwang, Fatih Porikli
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 text prompt tuning (ablation) | SAN · CUBper (K=5) | IoUper: 68.25 -> 69.70 | Improved |
| add text prompt tuning (ablation) | SAN · CUBper (K=5) | IoUper precision: 92.25 -> 74.75 | Hurt |
| add text prompt tuning (ablation) | SAN · CUBper (K=5) | IoUper recall: 72.95 -> 91.04 | Improved |
| add negative mask proposal to text prompt tuning (ablation) | SAN · CUBper (K=5) | IoUper: 69.70 -> 73.71 | Improved |
| add negative mask proposal to text prompt tuning (ablation) | SAN · CUBper (K=5) | IoUper precision: 74.75 -> 80.07 | Improved |
| add visual embedding injection to text prompt tuning alone (ablation) | SAN · CUBper (K=5) | IoUper: 69.70 -> 65.94 | Hurt |
| add visual embedding injection to text prompt tuning plus negative mask (ablation) | SAN · CUBper (K=5) | IoUper: 73.71 -> 76.80 | Improved |
| add visual embedding injection to text prompt tuning plus negative mask (ablation) | SAN · CUBper (K=5) | mIoU: 77.89 -> 78.29 | Improved |
| apply personalization method to SAN | SAN · FSSper | IoUper: 41.08 -> 53.56 | Improved |
| apply personalization method to SAN | SAN · ADEper | IoUper: 6.88 -> 22.67 | Improved |
| apply personalization method to ODISE | ODISE · CUBper | IoUper: 0.02 -> 5.76 | Improved |
| apply personalization method to ODISE | ODISE · FSSper | mIoU: 23.86 -> 22.48 | Hurt |
Closest papers by meaning
- Emergent Open-Vocabulary Semantic Segmentation from Off-the-shelf Vision-Language Models (CVPR 2024 · similarity 0.89)
- Training-free Open-Vocabulary Semantic Segmentation via Diverse Prototype Construction and Sub-region Matching (AAAI 2025 · similarity 0.88)
- Training-Free Open-Vocabulary Segmentation with Offline Diffusion-Augmented Prototype Generation (CVPR 2024 · similarity 0.87)
- Relationship Prompt Learning is Enough for Open-Vocabulary Semantic Segmentation (NeurIPS 2024 · similarity 0.86)
- Open-Vocabulary Segmentation with Semantic-Assisted Calibration (CVPR 2024 · similarity 0.86)
- Dual Semantic Guidance for Open Vocabulary Semantic Segmentation (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.
