AI Paper Atlas

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

TACS: Taxonomy Adaptive Cross-Domain Semantic Segmentation

Rui Gong, Martin Danelljan, Dengxin Dai, Danda Pani Paudel, Ajad Chhatkuli, Fisher Yu, Luc Van Gool

ECCV 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 11 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 UCT (uncertainty-rectified contrastive learning) to DACS (ablation)DACS · SYNTHIA->Cityscapes (UDA, 16 classes)mIoU: 48.34 -> 51.45Improved
replace CT with uncertainty-rectified UCT (ablation)DACS+CT · SYNTHIA->Cityscapes (UDA, 16 classes)mIoU: 49.47 -> 51.45Improved
add CT to BMS in open taxonomy (ablation)TACS (M) · SYNTHIA->Cityscapes open, all classesmIoU: 43.44 -> 45.86Improved
add UCT to BMS in open taxonomy (ablation)TACS (M) · SYNTHIA->Cityscapes open, all classesmIoU: 43.44 -> 45.99Improved
add pseudo-label relabeling RL (ablation)TACS (M+UCT) · SYNTHIA->Cityscapes open, 6 new classesmIoU: 16.92 -> 22.85Improved
add RL to M+UCT in open taxonomy (all classes) (ablation)TACS (M+UCT) · SYNTHIA->Cityscapes open, all classesmIoU: 45.99 -> 49.72Improved
add stochastic label mapping SLM to BMS (ablation)TACS (M) · GTA5->Cityscapes coarse-to-fine, 6 fine classesmIoU: 34.76 -> 52.28Improved
add UCT to M+SLM (ablation)TACS (M+SLM) · GTA5->Cityscapes coarse-to-fine, all classesmIoU: 53.68 -> 55.27Improved
add RL to M+SLM+UCT (ablation)TACS · GTA5->Cityscapes coarse-to-fine, all classesmIoU: 55.27 -> 55.68Improved
add SLM to baseline methods (DACS)DACS · GTA5->Cityscapes coarse-to-fine, all classesmIoU: 35.57 -> 18.98Hurt
add SLM to baseline methods (ADVENT)ADVENT · GTA5->Cityscapes coarse-to-fine, all classesmIoU: 37.25 -> 36.41Hurt
add SLM to M (ablation)TACS (M) · Synscapes->Cityscapes implicit-overlap, 3 classesmIoU: 47.94 -> 53.18Improved

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