Research map / Detection and segmentation / Open-set and few-shot detection
WOW-Seg: A Word-free Open World Segmentation Model
Danyang Li, Tianhao Wu, Bin Lin, Zhenyuan Chen, Yang Zhang, Yuxuan Li, Ming-Ming Cheng, Xiang Li
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 |
|---|---|---|---|
| train with multiple masks per sample instead of single mask (ablation) | WOW-Seg · LVIS | Semantic IoU: 74.70 -> 80.10 | Improved |
| add region decoupling of mask tokens (Cascade Attention Mask) (ablation) | WOW-Seg MM · LVIS | Semantic IoU: 80.10 -> 82.18 | Improved |
| add output decoupling of object names (Cascade Attention Mask) (ablation) | WOW-Seg MM · LVIS | Semantic IoU: 80.10 -> 81.94 | Improved |
| add both region and output decoupling (full Cascade Attention Mask) (ablation) | WOW-Seg MM · LVIS | Semantic IoU: 80.10 -> 82.35 | Improved |
| add both region and output decoupling (full Cascade Attention Mask) (ablation) | WOW-Seg MM · PACO | Semantic IoU: 75.49 -> 79.22 | Improved |
| use Mask2Token instead of Fore2Token (ablation) | WOW-Seg · LVIS | Semantic IoU: 72.54 -> 74.70 | Improved |
| use Mask2Token instead of Blur2Token (ablation) | WOW-Seg · PACO | Semantic IoU: 64.35 -> 66.04 | Improved |
| use context scale 1.5 instead of 2 in Mask2Token (ablation) | WOW-Seg · LVIS | Semantic IoU: 82.35 -> 82.59 | No clear effect |
| increase context scale from 2 to 3.5 (ablation) | WOW-Seg · LVIS | Semantic IoU: 82.35 -> 81.89 | Hurt |
| upgrade base VLM from InternVL2 to InternVL3 (ablation) | WOW-Seg · LVIS | Semantic IoU: 80.8 -> 82.4 | Improved |
| upgrade base VLM from InternVL2 to InternVL3 (ablation) | WOW-Seg · PACO | Semantic IoU: 74.0 -> 79.2 | Improved |
| use rotated bounding-box prompts instead of ground-truth masks (ablation) | WOW-Seg · LVIS | Semantic similarity: 89.7 -> 87.3 | Hurt |
Closest papers by meaning
- OpenWorldSAM: Extending SAM2 for Universal Image Segmentation with Language Prompts (NeurIPS 2025 · similarity 0.89)
- Exploring Simple Open-Vocabulary Semantic Segmentation (CVPR 2025 · similarity 0.89)
- Leveraging Depth and Language for Open-Vocabulary Domain-Generalized Semantic Segmentation (NeurIPS 2025 · similarity 0.88)
- Recognize Any Regions (NeurIPS 2024 · similarity 0.88)
- Open-World Semantic Segmentation Including Class Similarity (CVPR 2024 · similarity 0.88)
- v-CLR: View-Consistent Learning for Open-World Instance Segmentation (CVPR 2025 · 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.
