AI Paper Atlas

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

Focus on Your Target: A Dual Teacher-Student Framework for Domain-Adaptive Semantic Segmentation

Xinyue Huo, Lingxi Xie, Wengang Zhou, Houqiang Li, Qi Tian

ICCV 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 26 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
increase the proportion of target-domain data in a single teacher-student model (<T,T> mixing) (ablation)DAFormer · GTAv->CityscapesmIoU: 68.3 -> 67.2Hurt
use the dual teacher-student framework together with more target data (ablation)DAFormer · GTAv->CityscapesmIoU: 67.2 -> 69.7Improved
add bidirectional learning on top of DTS with Focus on Your Target (ablation)DTS (DAFormer) · GTAv->CityscapesmIoU: 69.7 -> 71.2Improved
add Focus on Your Target (more target data) on top of DTS with bidirectional learning (ablation)DTS (DAFormer) · SYNTHIA->Cityscapes (16 classes)mIoU: 61.2 -> 63.7Improved
add DTS to MIC, HRDA and DAFormer baselinesMIC/HRDA/DAFormer · GTAv->CityscapesmIoU: +2.9, +1.4, +0.6Improved
choose Setting A vs B using pseudo-label confidence criterion (ablation)DTS (DAFormer) · GTAv->Cityscapes vs SYNTHIA->CityscapesmIoU: GTAv B 71.2 vs A 70.3; SYNTHIA A 63.8 vs B 61.2Mixed
each group uses only the other group's teacher for pseudo labels (ablation)DTS (DAFormer) · GTAv->CityscapesmIoU: 68.3 -> 68.5No clear effect
use student f1,t+1 st instead of teacher f1,t+1 te for group 2 pseudo labels (learning from future) (ablation)DTS (DAFormer) · GTAv->CityscapesmIoU: 69.5 -> 71.3Improved
apply DTS to CNN backbone (ResNet101 DeepLabV2)DACS and DAFormer · GTAv->Cityscapes (ResNet101)mIoU: 53.9 -> 55.2; 56.0 -> 59.9Improved
apply DTS to semi-supervised segmentation vs Mean TeacherPASCAL VOC DeepLabV3+ · PASCAL VOC semi-supervisedmIoU: +3.5, +1.7, +0.8 (1/16, 1/8, 1/4)Improved
use only <T,T> or only <S,T> mixing for the second group (ablation)DTS (DAFormer) · SYNTHIA->Cityscapes (16 classes)mIoU: 63.8 -> 61.1 / 59.4Hurt

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