Research map / Detection and segmentation / Open-set and few-shot detection
Prototype-Anchored Generalized Manifold Regression for Unknown-Domain Object Detection
Zihao Zhang, Aming Wu, Yang Li, Yahong Han
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 |
|---|---|---|---|
| replace SE-COT with MR-DCoT (add visual chain and prototype anchoring) | Faster R-CNN R-101 · Day Clear to Night Rainy | mAP: 24.5 -> 28.1 | Improved |
| replace SE-COT with MR-DCoT | Faster R-CNN Swin-T · Day Clear to Night Rainy | mAP: 33.74 -> 36.44 | Improved |
| replace SE-COT with MR-DCoT | Faster R-CNN Swin-T · Day Clear to Dusk Rainy | mAP: 49.45 -> 53.21 | Improved |
| replace SE-COT with MR-DCoT | Faster R-CNN Swin-T · Day Clear to Day Foggy | mAP: 44.99 -> 48.27 | Improved |
| replace SE-COT with MR-DCoT | Faster R-CNN Swin-T · Day Clear to Night Sunny | mAP: 52.75 -> 54.63 | Improved |
| replace SE-COT with MR-DCoT | YOLO CSPNet · Day Clear to Night Rainy | mAP: 23.9 -> 27.0 | Improved |
| replace PGST with MR-DCoT | GLIP-T · Day Clear to Night Sunny | mAP: 47.9 -> 50.2 | Improved |
| replace PGST with MR-DCoT | GLIP-T · Day Clear to Day Foggy | mAP: 42.5 -> 46.9 | Improved |
| replace SE-COT with MR-DCoT | Faster R-CNN Swin-T · VOC to Watercolor | mAP: 60.7 -> 63.2 | Improved |
| replace SE-COT with MR-DCoT | Faster R-CNN Swin-T · VOC to Comic | mAP: 36.9 -> 40.4 | Improved |
| replace SE-COT with MR-DCoT | Faster R-CNN Swin-T · VOC to Clipart | mAP: 42.5 -> 45.6 | Improved |
| apply MR-DCoT versus ULDA | segmentation model · Cityscapes to ACDC Night | mIoU: 25.40 -> 27.20 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Faster R-CNN — Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (TPAMI 2016) · better on 4 of 4 shared results
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
- Style Evolving along Chain-of-Thought for Unknown-Domain Object Detection (CVPR 2025 · 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 0.89)
- Generalized Diffusion Detector: Mining Robust Features from Diffusion Models for Domain-Generalized Detection (CVPR 2025 · similarity 0.88)
- Object-Aware Domain Generalization for Object Detection (AAAI 2024 · similarity 0.88)
- Generalize or Detect? Towards Robust Semantic Segmentation Under Multiple Distribution Shifts (NeurIPS 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.
