Research map / Detection and segmentation / Open-set and few-shot detection
Towards Sparsely Annotated Open World Object Detection
HEEJU HAN, AJEONG KIM, Jinsun Park
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 KTRM to CROWD (ablation) | CROWD · SA-OWOD Hard Task 1 | K-mAP: 49.29 -> 51.90 (+2.61) | Improved |
| add KTRM to CROWD (ablation) | CROWD · SA-OWOD Hard Task 1 | U-Recall: 49.80 -> 50.66 (+0.86) | Improved |
| add DDTG to CROWD (ablation) | CROWD · SA-OWOD Hard Task 1 | K-mAP: 49.29 -> 51.08 (+1.79) | Improved |
| add DDTG to CROWD (ablation) | CROWD · SA-OWOD Hard Task 1 | U-Recall: 49.80 -> 50.26 (+0.46) | Improved |
| add both KTRM and DDTG to CROWD (ablation) | CROWD · SA-OWOD Hard Task 1 | K-mAP: 49.29 -> 54.09 (+4.80) | Improved |
| add both KTRM and DDTG to CROWD (ablation) | CROWD · SA-OWOD Hard Task 1 | U-Recall: 49.80 -> 51.85 (+2.05) | Improved |
| raise objectness threshold from 0.1 to 0.2 (ablation) | DPOD · SA-OWOD Hard Task 1 | U-Recall: 47.68 -> 51.85 | Improved |
| raise objectness threshold from 0.2 to 0.3 (ablation) | DPOD · SA-OWOD Hard Task 1 | U-Recall: 51.85 -> 51.40 | Hurt |
| raise similarity threshold from 0.90 to 0.95 (ablation) | DPOD · SA-OWOD Hard Task 1 | U-Recall: 46.26 -> 51.85 | Improved |
| raise similarity threshold from 0.85 to 0.95 (ablation) | DPOD · SA-OWOD Hard Task 1 | K-mAP: 52.53 -> 54.09 | Improved |
Closest papers by meaning
- Open-World Objectness Modeling Unifies Novel Object Detection (CVPR 2025 · similarity 0.91)
- Exploring Orthogonality in Open World Object Detection (CVPR 2024 · similarity 0.90)
- OW-OVD: Unified Open World and Open Vocabulary Object Detection (CVPR 2025 · similarity 0.90)
- Hyp-OW: Exploiting Hierarchical Structure Learning with Hyperbolic Distance Enhances Open World Object Detection (AAAI 2024 · similarity 0.89)
- Looking Beyond the Known: Towards a Data Discovery Guided Open-World Object Detection (NeurIPS 2025 · similarity 0.89)
- Semi-supervised Open-World Object Detection (AAAI 2024 · similarity 0.89)
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.
