AI Paper Atlas

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

Learning Pseudo-Relations for Cross-domain Semantic Segmentation

Dong Zhao, Shuang Wang, Qi Zang, Dou Quan, Xiutiao Ye, Rui Yang, Licheng Jiao

ICCV 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 38 citations (OpenAlex)

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 pseudo-relation learning (L_pr) on top of SAC + copy-paste (ablation)SAC self-training · GTA5 -> CityscapesmIoU: 55.8 -> 59.6Improved
use threshold-free L_pr instead of thresholded L_pr-hat (ablation)RTea · GTA5 -> CityscapesmIoU: 58.9 -> 59.6Improved
also perform relation learning on source domain (ablation)RTea · GTA5 -> CityscapesmIoU: 59.6 -> 59.6No clear effect
add distillation retraining after RTea (ablation)RTea · GTA5 -> CityscapesmIoU: 59.6 -> 61.9Improved
fuse low-level RGBXY relations with high-level pseudo-label relations (ablation)RTea · GTA5 -> CityscapesmIoU: 56.8 / 57.8 -> 59.6Improved
include reliable-unreliable pixel pairs in relation learning (ablation)RTea · GTA5 -> CityscapesmIoU: 57.2 -> 59.3 (adding R-U to R-R)Improved
add unreliable-unreliable pairs (ablation)RTea · GTA5 -> CityscapesmIoU: 59.3 -> 59.6Improved
restrict relations to local grids instead of global image (ablation)RTea · GTA5 -> CityscapesmIoU: global R-U 51.4 (-4.4) vs local grid R-U 57.9 (+2.1)Improved
apply RTea on different pseudo-label selection strategies (PD, CD, AD, HT) (ablation)online self-training baselines · GTA5 -> CityscapesmIoU: 55.0 -> 58.8 (PD); 54.4 -> 56.8 (CD); 53.2 -> 54.8 (AD); 55.8 -> 59.6 (HT)Improved
vary threshold theta and decay beta (ablation)RTea · GTA5 -> CityscapesmIoU: 58.8 to 59.6 across settingsNo clear effect
use the same Gaussian metric for low- and high-level relations (ablation)RTea · GTA5 -> CityscapesmIoU / time per batch: 59.6 -> 59.6 mIoU; 40ms -> 29msNo clear effect
add RTea to Daformer and HRDA backbonesDaformer, HRDA · GTA5 -> CityscapesmIoU: 68.3 -> 70.6 (Daformer); 73.8 -> 74.7 (HRDA)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