AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Rein++: Efficient Generalization and Adaptation for Semantic Segmentation With Vision Foundation Models

Zhixiang Wei, Xiaoxiao Ma, Ruishen Yan, Tao Tu, Huaian Chen, Jinjin Zheng, Yi Jin, Enhong Chen

TPAMI 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Domain-generalized segmentation

This paper tried a common change: Larger LoRA rank

raise LoRA rank r from 16 to 4 · GTAV -> Citys.+BDD.+Map. (avg) · mIoU: 67.5 -> 66.8 Hurt

What 233 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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 changedWhereMeasuredEffect
add Rein-G to a frozen DINOv2-LargeFrozen DINOv2-L · GTAV -> Citys.+BDD.+Map. (avg)mIoU: 65.6 -> 67.5Improved
fully fine-tune DINOv2-Large instead of freezingDINOv2-L · GTAV -> Citys.+BDD.+Map. (avg)mIoU: 65.6 -> 61.7Hurt
add Rein-G to frozen CLIP-LargeCLIP-L · GTAV -> Citys.+BDD.+Map. (avg)mIoU: 52.9 -> 59.2Improved
add Rein-G to frozen DINOv2-GiantDINOv2-G · GTAV -> Citys.+BDD.+Map. (avg)mIoU: 65.1 -> 68.4Improved
add Rein-core (ablation)Frozen DINOv2-L · GTAV -> CityscapesmIoU: 68.0 -> 69.9Improved
add Rein-link (ablation)Rein-core · GTAV -> CityscapesmIoU: 69.9 -> 70.1Improved
add multi-head (ablation)Rein-lora · GTAV -> CityscapesmIoU: 70.1 -> 70.8Improved
add GELU (ablation)Rein-G with multi-head · GTAV -> CityscapesmIoU: 70.8 -> 70.9Improved
raise LoRA rank r from 16 to 4 (ablation)Rein-G · GTAV -> Citys.+BDD.+Map. (avg)mIoU: 67.5 -> 66.8Hurt
increase token length from 100 to 200 (ablation)Rein-G · GTAV -> CityscapesmIoU: 70.7 -> 68.9Hurt
add Rein-G to Rein-A (ablation)Rein-A (DINOv2-L) · GTA -> Cityscapes valmIoU: 71.5 -> 76.9Improved
add L_mix loss (ablation)Rein-A (DINOv2-L) · GTA -> Cityscapes valmIoU: 71.6 -> 76.9Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most 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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy