Research map / Detection and segmentation / Open-set and few-shot detection
Rethinking Open-Set Object Detection: Issues, A New Formulation, and Taxonomy
Yusuke Hosoya, Masanori Suganuma, Takayuki Okatani
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 |
|---|---|---|---|
| use a dedicated unknown-detection method (OpenDet) instead of the naive Faster RCNN baseline | Faster RCNN · OSOD-III Animal | AP_unk: 35.3 -> 33.0 | No clear effect |
| use FCOS instead of Faster RCNN as the naive baseline | naive baseline · OSOD-III Animal | AP_unk: 35.3 -> 41.8 | Improved |
| add OrthogonalDet orthogonality-based objectness | OSOD detector · OSOD-III Animal | AP_unk: 35.3 -> 8.9 | Hurt |
| add OrthogonalDet | OSOD detector · OSOD-III Animal | AP_known: 37.8 -> 44.8 | Improved |
| use OpenDet instead of Faster RCNN | Faster RCNN · OSOD-III Vehicle | AP_unk: 17.0 -> 14.4 | Hurt |
| use OpenDet instead of Faster RCNN | Faster RCNN · OSOD-III CUB200 | AP_unk: 24.2 -> 27.0 | Improved |
| use OpenDet instead of Faster RCNN | Faster RCNN · OSOD-III MTSD | AP_unk: 3.1 -> 9.9 | Improved |
| use OpenDet instead of Faster RCNN | Faster RCNN · OSOD-III Carnivore | AP_unk: 30.4 -> 28.5 | No clear effect |
| use OpenDet instead of Faster RCNN | Faster RCNN · OSOD-III Land Vehicle | AP_unk: 5.6 -> 14.3 | Improved |
| use ORE instead of Faster RCNN | Faster RCNN · OSOD-III Vehicle | AP_unk: 17.0 -> 0.3 | Hurt |
Closest papers by meaning
- Expanding Low-Density Latent Regions for Open-Set Object Detection (CVPR 2022 · similarity 0.92)
- UC-OWOD: Unknown-Classified Open World Object Detection (ECCV 2022 · similarity 0.90)
- YolOOD: Utilizing Object Detection Concepts for Multi-Label Out-of-Distribution Detection (CVPR 2024 · similarity 0.90)
- Towards Evidential and Class Separable Open Set Object Detection (AAAI 2024 · similarity 0.89)
- UMB: Understanding Model Behavior for Open-World Object Detection (NeurIPS 2024 · similarity 0.89)
- OW-OVD: Unified Open World and Open Vocabulary Object Detection (CVPR 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.
