Research map / Label-efficient and robust learning / Domain adaptation and generalization
QPrompt-R1: Real-Time Reasoning for Domain-Generalized Semantic Segmentation via Group-Relative Query Alignment
Fengyuan Lu, Zixuan Duan, Xunzhi Xiang, Zhicheng Zhang, Wenbin Li, Yang Gao, Qi Fan
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 QPrompt learnable queries in final ViT block instead of MLP head (ablation) | DINOv2-L segmentation · GTAV->Citys+BDD+Map avg | mIoU: 59.9 -> 62.3 | Improved |
| add image-prototype alignment loss (ablation) | QPrompt · GTAV->Citys+BDD+Map avg | mIoU: 62.3 -> 62.6 | Improved |
| add group-relative alignment reward (ablation) | QPrompt · GTAV->Citys+BDD+Map avg | mIoU: 62.6 -> 63.7 | Improved |
| add KL divergence to EMA reference model (ablation) | QPrompt-R1 · GTAV->Citys+BDD+Map avg | mIoU: 63.7 -> 64.1 | Improved |
| add GRQA as plug-in training | REIN · GTAV->Real avg | mIoU: 64.3 -> 65.5 | Improved |
| add GRQA as plug-in training | SoMA · GTAV->Real avg | mIoU: 68.2 -> 68.8 | Improved |
| use GRQA reward instead of DINO-R1 reward (ablation) | QPrompt · GTAV->Citys+BDD+Map avg | mIoU: 62.9 -> 64.1 | Improved |
| add any reward (DINO-R1) versus none (ablation) | QPrompt · GTAV->Citys+BDD+Map avg | mIoU: 62.3 -> 62.9 | Improved |
| add QPrompt then GRQA on CLIP-L backbone (ablation) | CLIP-L · GTAV->Citys | mIoU: 50.4 -> 51.7 -> 53.2 | Improved |
| add QPrompt then GRQA on SAM-H backbone (ablation) | SAM-H · GTAV->Citys | mIoU: 54.7 -> 55.8 -> 57.2 | Improved |
| replace Mask2Former transformer decoder with MLP head (ablation) | Mask2Former · GTAV->Citys | mIoU: 63.7 -> 61.3 | Hurt |
| remove pixel decoder from Mask2Former (ablation) | Mask2Former · GTAV->Citys | mIoU: 63.7 -> 62.9 | Mixed |
Closest papers by meaning
- Stronger Fewer & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation (CVPR 2024 · similarity 0.86)
- Collaborating Foundation Models for Domain Generalized Semantic Segmentation (CVPR 2024 · similarity 0.86)
- Leveraging Depth and Language for Open-Vocabulary Domain-Generalized Semantic Segmentation (NeurIPS 2025 · similarity 0.86)
- RMP-SAM: Towards Real-Time Multi-Purpose Segment Anything (ICLR 2025 · similarity 0.86)
- Better to Teach than to Give: Domain Generalized Semantic Segmentation via Agent Queries with Diffusion Model Guidance (ICML 2025 · similarity 0.85)
- FisherTune: Fisher-Guided Robust Tuning of Vision Foundation Models for Domain Generalized Segmentation (CVPR 2025 · similarity 0.85)
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.
