Research map / Detection and segmentation / Open-set and few-shot detection
ASGS: Single-Domain Generalizable Open-Set Object Detection via Adaptive Subgraph Searching
Yuxuan Yuan, Luyao Tang, Yixin Chen, Chaoqi Chen, Yue Huang, Xinghao Ding
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 Subgraph-wise Unknown-class Learning (SUL) (ablation) | ASGS · Cityscapes->Foggy Cityscapes het-sem, 3 unknown classes | ARu: 0.00 -> 2.87 | Improved |
| add SUL (ablation) | ASGS · Cityscapes->Foggy Cityscapes het-sem, 3 unknown classes | mAPk: 42.60 -> 41.09 | Hurt |
| add SUL (ablation) | ASGS · Cityscapes->Foggy Cityscapes het-sem, 3 unknown classes | WI: 0.292 -> 0.314 | Hurt |
| add Class-wise Embedding Compaction (CEC) (ablation) | ASGS · Cityscapes->Foggy Cityscapes het-sem, 3 unknown classes | mAPk: 36.10 -> 41.09 | Improved |
| add CEC (ablation) | ASGS · Cityscapes->Foggy Cityscapes het-sem, 3 unknown classes | ARu: 2.63 -> 2.87 | Improved |
| add Adaptive Subgraph Searching (ASS) in SUL (ablation) | ASGS · Cityscapes->Foggy Cityscapes het-sem, 3 unknown classes | mAPk: 37.31 -> 41.09 | Improved |
| add ASS in SUL (ablation) | ASGS · Cityscapes->Foggy Cityscapes het-sem, 3 unknown classes | ARu: 2.76 -> 2.87 | Improved |
| add ASS in SUL (ablation) | ASGS · Cityscapes->Foggy Cityscapes het-sem, 3 unknown classes | AOSE: 169 -> 185 | Hurt |
| ASGS instead of D-DETR baseline | ASGS · Cityscapes->Foggy Cityscapes het-sem, 3 unknown classes | mAPk: 37.69 -> 41.09 | Improved |
| ASGS instead of D-DETR baseline | ASGS · Pascal VOC->Clipart1K 6 unknown classes | mAPk: 18.34 -> 21.66 | Improved |
| ASGS instead of D-DETR baseline | ASGS · Cityscapes->BDD100K het-sem 3 unknown classes | mAPk: 13.24 -> 13.57 | Improved |
| set K and M to 5, delta 0.6 (ablation) | ASGS · Cityscapes->Foggy Cityscapes het-sem, 3 unknown classes | mAPk | Mixed |
Later papers that compared with this method
1 later accepted paper reports ASGS as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Learning Latent Concepts for Detecting Out-of-Distribution Objects (CVPR 2026 · better on 3 of 3 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- PROB — PROB: Probabilistic Objectness for Open World Object Detection (CVPR 2023) · better on 0 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
- Object-Aware Domain Generalization for Object Detection (AAAI 2024 · similarity 0.89)
- Improving Single Domain-Generalized Object Detection: A Focus on Diversification and Alignment (CVPR 2024 · similarity 0.89)
- Towards Single-Source Domain Generalized Object Detection via Causal Visual Prompts (NeurIPS 2025 · similarity 0.87)
- Generalized Diffusion Detector: Mining Robust Features from Diffusion Models for Domain-Generalized Detection (CVPR 2025 · similarity 0.87)
- G-NAS: Generalizable Neural Architecture Search for Single Domain Generalization Object Detection (AAAI 2024 · similarity 0.87)
- CAT: Exploiting Inter-Class Dynamics for Domain Adaptive Object Detection (CVPR 2024 · 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.
