Research map / Detection and segmentation / Open-set and few-shot detection
UC-OWOD: Unknown-Classified Open World Object Detection
Zhiheng Wu, Yue Lu, Xingyu Chen, Zhengxing Wu, Liwen Kang, Junzhi Yu
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 the unknown-discriminative classification head (UCH) (ablation) | Faster R-CNN with SUC · UC-OWOD Task 1 | UC-Recall: 0 -> 2.3915 | Improved |
| add similarity-based unknown classification (SUC) on top of UCH (ablation) | UCH model · UC-OWOD Task 1 | UC-mAP: 0.0176 -> 0.1343 | Improved |
| add SUC on top of UCH (ablation) | UCH model · UC-OWOD Task 1 | UC-Recall: 1.4796 -> 2.3915 | Improved |
| add SUC on top of UCH (ablation) | UCH model · UC-OWOD Task 1 | WI: 0.0155 -> 0.0136 | Improved |
| add SUC on top of UCH (ablation) | UCH model · UC-OWOD Task 1 | A-OSE: 9185 -> 9294 | Hurt |
| add SUC without UCH (ablation) | Faster R-CNN · UC-OWOD Task 1 | UC-Recall: 0 -> 0 | No clear effect |
| add unknown clustering refinement (UCR) | Ours · UC-OWOD Task 2 | UC-mAP: 0.0862 -> 0.1694 | Improved |
| add UCR | Ours · UC-OWOD Task 2 | UC-Recall: 2.6926 -> 3.4431 | Improved |
| add UCR | Ours · UC-OWOD Task 3 | UC-mAP: 0.0249 -> 0.0744 | Improved |
| add UCR | Ours · UC-OWOD Task 3 | UC-Recall: 4.8077 -> 8.7303 | Improved |
| use 5 pseudo-GT per image instead of 1 (ablation) | Ours (NMS 0.3, delta 0.3) · UC-OWOD Task 1 | UC-Recall: 0.9314 -> 2.3915 | Improved |
| raise delta from 0.3 to 0.7 (ablation) | Ours (NMS 0.3, 5 pseudo-GT) · UC-OWOD Task 1 | UC-Recall: 2.3915 -> 1.6730 | Hurt |
Closest papers by meaning
- UMB: Understanding Model Behavior for Open-World Object Detection (NeurIPS 2024 · similarity 0.91)
- OW-OVD: Unified Open World and Open Vocabulary Object Detection (CVPR 2025 · similarity 0.90)
- Semi-supervised Open-World Object Detection (AAAI 2024 · similarity 0.89)
- Open-World Objectness Modeling Unifies Novel Object Detection (CVPR 2025 · similarity 0.88)
- Detecting Open World Objects via Partial Attribute Assignment (CVPR 2025 · similarity 0.88)
- Hyp-OW: Exploiting Hierarchical Structure Learning with Hyperbolic Distance Enhances Open World Object Detection (AAAI 2024 · 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.
