AI Paper Atlas

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

Hard-Aware Instance Adaptive Self-Training for Unsupervised Cross-Domain Semantic Segmentation

Chuang Zhu, Kebin Liu, Wenqi Tang, Ke Mei, Jiaqi Zou, Tiejun Huang

TPAMI 2025 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 12 citations (OpenAlex)

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 changedWhereMeasuredEffect
add instance adaptive selector (IAS) (ablation)HIAST · GTA5 -> CityscapesmIoU: 43.8 -> 49.5Improved
add confident region KLD minimization (Rc) (ablation)HIAST · GTA5 -> CityscapesmIoU: 49.5 -> 50.5Improved
add ignored region entropy minimization (Ri) (ablation)HIAST · GTA5 -> CityscapesmIoU: 50.5 -> 51.5Improved
add hard-aware pseudo-label augmentation (HPLA) (ablation)HIAST · GTA5 -> CityscapesmIoU: 51.5 -> 55.7Improved
add ignored region consistency constraint (Rcst) (ablation)HIAST · GTA5 -> CityscapesmIoU: 55.7 -> 56.3Improved
add EMA in IAS (ablation)HIAST · GTA5 -> CityscapesmIoU: 55.2 -> 56.3Improved
add warm-up model before self-training (ablation)HIAST · GTA5 -> CityscapesmIoU: 35.6 -> 43.8Improved
replace AdaptSeg with SePiCo as warm-up modelHIAST · GTA5 -> CityscapesmIoU: 56.3 -> 64.1Improved
apply HIAST to DAFormerDAFormer · GTA5 -> CityscapesmIoU: 68.3 -> 69.5Improved
apply HIAST to HRDAHRDA · GTA5 -> CityscapesmIoU: 73.8 -> 74.5Improved
apply HIAST to AdaptSeg (one round)AdaptSeg · GTA5 -> CityscapesmIoU: 42.4 -> 53.6Improved
apply HIAST to CPSL (one round)CPSL · GTA5 -> CityscapesmIoU: 60.8 -> 63.0Improved

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