Research map / Label-efficient and robust learning / Domain adaptation and generalization
GeCo: Geometry-Consistent Regularization for Domain Generalized Semantic Segmentation
Qi Zang, Dong Zhao, Nan Pu, Wenjing Li, Zhun Zhong, Meng Wang
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 random Gaussian perturbation with curvature-guided perturbation (both with MSE) (ablation) | GeCo · GTA5 -> Citys+BDD+Map (DINOv2-L) | Avg mIoU: 62.8 -> 65.7 | Improved |
| replace random perturbation with curvature-guided perturbation (ablation) | GeCo · GTA5 -> Citys+BDD+Map (EVA02-L) | Avg mIoU: 64.0 -> 65.3 | Improved |
| add geodesic-based regularization on top of curvature-guided perturbation (replace MSE) (ablation) | GeCo · GTA5 -> Citys+BDD+Map (DINOv2-L) | Avg mIoU: 65.7 -> 67.7 | Improved |
| add geodesic-based regularization on top of curvature-guided perturbation (replace MSE) (ablation) | GeCo · GTA5 -> Citys+BDD+Map (EVA02-L) | Avg mIoU: 65.3 -> 66.3 | Improved |
| use geodesic regularization with random perturbation instead of MSE (ablation) | random perturbation baseline · GTA5 -> Citys+BDD+Map (DINOv2-L) | Avg mIoU: 62.8 -> 64.1 | Improved |
| add random perturbation with MSE consistency to full fine-tuning (ablation) | EVA02-L · GTA5 -> Citys+BDD+Map | Avg mIoU: 61.0 -> 64.0 | Improved |
| plug GeCo into Rein | Rein (DINOv2-L) · GTA5 -> Citys+BDD+Map | Avg mIoU: 64.3 -> 66.3 | Improved |
| plug GeCo into FADA | FADA (DINOv2-L) · GTA5 -> Citys+BDD+Map | Avg mIoU: 66.1 -> 66.4 | Improved |
| GeCo vs SoMA in multi-source setting | GeCo · GTA5+SYNTHIA -> Citys+BDD+Map | Avg mIoU: 70.8 -> 71.1 | Mixed |
| add GeCo to RPL open-set pipeline instead of Rein | RPL · Cityscapes -> MUAD | AP: 51.8 -> 58.6 | 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.
- FisherTune — FisherTune: Fisher-Guided Robust Tuning of Vision Foundation Models for Domain Generalized Segmentation (CVPR 2025) · better on 3 of 3 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
- Stronger Fewer & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation (CVPR 2024 · similarity 0.89)
- FisherTune: Fisher-Guided Robust Tuning of Vision Foundation Models for Domain Generalized Segmentation (CVPR 2025 · similarity 0.89)
- A Simple Recipe for Language-guided Domain Generalized Segmentation (CVPR 2024 · similarity 0.89)
- Collaborating Foundation Models for Domain Generalized Semantic Segmentation (CVPR 2024 · similarity 0.89)
- Leveraging Depth and Language for Open-Vocabulary Domain-Generalized Semantic Segmentation (NeurIPS 2025 · similarity 0.89)
- Exploring Semantic Consistency and Style Diversity for Domain Generalized Semantic Segmentation (AAAI 2025 · similarity 0.89)
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.
