AI Paper Atlas

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

CDAC: Cross-domain Attention Consistency in Transformer for Domain Adaptive Semantic Segmentation

Kaihong Wang, Donghyun Kim, Rogerio Feris, Margrit Betke

ICCV 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 38 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 cross-domain prediction consistency loss (T2S and S2T) (ablation)DAFormer · GTAV-to-CityscapesmIoU: 68.3 -> 69.1Improved
add cross-domain attention consistency loss alone (ablation)DAFormer · GTAV-to-CityscapesmIoU: 68.3 -> 68.6Improved
add attention consistency loss on top of prediction consistency (ablation)DAFormer + CDAC · GTAV-to-CityscapesmIoU: 69.1 -> 69.6Improved
add attention consistency loss reduces seed variance (ablation)DAFormer · GTAV-to-CityscapesmIoU std: 0.7 -> 0.2Improved
stop gradient on query vectors in cross-domain branches (ablation)CDAC · GTAV-to-CityscapesmIoU: 69.1 -> 69.6Improved
perturb self-attention with random Gaussian noise (ablation)DAFormer · GTAV-to-CityscapesmIoU: 68.3 -> 67.3Hurt
inject uniform attention (context broadcasting) (ablation)DAFormer · GTAV-to-CityscapesmIoU: 68.3 -> 66.9Hurt
inject uniform attention (context broadcasting) (ablation)DAFormer · Synthia-to-CityscapesmIoU: 60.9 -> 59.1Hurt
add CDAC to HRDAHRDA · Synthia-to-CityscapesmIoU: 65.8 -> 68.7Improved
add CDAC to DAFormerDAFormer · Cityscapes-to-ACDC (test)mIoU: 55.4 -> 56.5Improved
add CDAC to Mean-Teacher baselineMean-Teacher · GTAV-to-Cityscapesaccuracy: 39.0% -> 41.18%Improved
add CDAC to DACSDACS · GTAV-to-Cityscapesaccuracy: 52.54% -> 53.79%Improved

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