Research map / Detection and segmentation / Open-set and few-shot detection
Novel Scenes & Classes: Towards Adaptive Open-set Object Detection
Wuyang Li, Xiaoqing Guo, Yixuan Yuan
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 structure-aware novel-class learning (SNL) (ablation) | Deformable DETR · Cityscapes->Foggy het-sem (5 novel) | ARn: 0.00 -> 3.31 | Improved |
| add structure-aware transfer learning (STL) (ablation) | Deformable DETR · Cityscapes->Foggy het-sem (5 novel) | mAPb: 42.38 -> 44.70 | Improved |
| combine SNL and STL (ablation) | Deformable DETR · Cityscapes->Foggy het-sem (5 novel) | ARn: 0.00 -> 4.08 | Improved |
| mix motif-based pseudo-label y3 with distance-based y2 (ablation) | STL · Cityscapes->Foggy het-sem (5 novel) | mAPb: 44.05 -> 45.55 | Improved |
| use 3 motifs instead of 5 in SNL (ablation) | SNL · Cityscapes->Foggy het-sem (5 novel) | mAPb: 45.55 -> 46.00 | Mixed |
| use 7 motifs instead of 5 in SNL (ablation) | SNL · Cityscapes->Foggy het-sem (5 novel) | AOSE: 649 -> 582 | Mixed |
| SOMA vs OW-DETR on base-class accuracy | OW-DETR · Cityscapes->Foggy het-sem (5 novel) | mAPb: 39.92 -> 45.55 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- OW-DETR — OW-DETR: Open-World Detection Transformer (CVPR 2022) · better on 2 of 2 shared results
- Deformable DETR — Deformable DETR: Deformable Transformers for End-to-End Object Detection (ICLR 2021) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Universal Domain Adaptive Object Detection via Dual Probabilistic Alignment (AAAI 2025 · similarity 0.88)
- Large Self-Supervised Models Bridge the Gap in Domain Adaptive Object Detection (CVPR 2025 · similarity 0.88)
- DA-Ada: Learning Domain-Aware Adapter for Domain Adaptive Object Detection (NeurIPS 2024 · similarity 0.88)
- SEEN-DA: SEmantic ENtropy guided Domain-aware Attention for Domain Adaptive Object Detection (CVPR 2025 · similarity 0.87)
- Open-Det: An Efficient Learning Framework for Open-Ended Detection (ICML 2025 · similarity 0.87)
- Differential Alignment for Domain Adaptive Object Detection (AAAI 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.
