Research map / Detection and segmentation / Open-set and few-shot detection
Decompose and Attribute: Boosting Generalizable Open-Set Object Detection via Objectness Score
Yuxuan Yuan, Lichen Wei, Luyao Tang, Chaoqi Chen, Zheyuan Cai, 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 objectness attribution (Att) (ablation) | DOAT · Cityscapes->Foggy (Table 4 'Foggy') | ARu: 0.01 -> 10.16 | Improved |
| add wavelet decomposition (Dec) (ablation) | DOAT · Cityscapes->Foggy (Table 4 'Foggy') | ARu: 7.43 -> 10.16 | Improved |
| add semantic-guided attribution (ablation) | DOAT · Pascal VOC->Clipart (Table 4 'Clipart') | ARu: 28.95 -> 34.92 | Improved |
| add semantic-guided attribution (ablation) | DOAT · Cityscapes->Foggy (Table 4 'Foggy') | mAPk: 37.58 -> 38.28 | Improved |
| add decomposition and attribution (ablation) | D-DETR · Pascal VOC->Clipart | ARu: 0.00 -> 34.92 | Improved |
| use FPS style basis instead of random interpolation (ablation) | LFSD · Cityscapes->Foggy (Table 4 'Foggy') | mAPk: 37.26 -> 38.28 | Improved |
| use FPS style basis instead of random interpolation (ablation) | LFSD · Cityscapes->BDD100K | mAPk: 13.66 -> 13.53 | Mixed |
| perturb only low-frequency instead of full features (ablation) | LFSD · Cityscapes->Foggy (Table 4 'Foggy') | mAPk: 37.42 -> 38.28 | Improved |
| vary attribution loss weight (ablation) | DOAT · Foggy / Clipart | mAPk, ARu | No clear effect |
| DOAT vs baselines on BDD100K | DOAT · Cityscapes->BDD100K | ARu: 1.82 vs PROB 1.83 | No clear effect |
Closest papers by meaning
- Open-World Objectness Modeling Unifies Novel Object Detection (CVPR 2025 · similarity 0.87)
- How to Evaluate the Generalization of Detection? A Benchmark for Comprehensive Open-Vocabulary Detection (AAAI 2024 · similarity 0.87)
- Exploring Orthogonality in Open World Object Detection (CVPR 2024 · similarity 0.87)
- OW-OVD: Unified Open World and Open Vocabulary Object Detection (CVPR 2025 · similarity 0.87)
- Object-Aware Domain Generalization for Object Detection (AAAI 2024 · similarity 0.87)
- Generative Region-Language Pretraining for Open-Ended Object Detection (CVPR 2024 · similarity 0.86)
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.
