AI Paper Atlas

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

Both Style and Distortion Matter: Dual-Path Unsupervised Domain Adaptation for Panoramic Semantic Segmentation

Xu Zheng, Jinjing Zhu, Yexin Liu, Zidong Cao, Chong Fu, Lin Wang

CVPR 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 36 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
use ERP and tangent images in dual paths instead of ERP in both paths (ablation)DPPASS-T · DensePASS testmIoU: 45.22 -> 49.53Improved
add intra-projection loss L_g (ablation)DPPASS-T · DensePASS testmIoU: 42.40 -> 50.12; +7.72Improved
add prediction consistency loss L_pc (ablation)DPPASS-T · DensePASS testmIoU: 42.40 -> 49.53; +7.13%Improved
add tangent-wise feature contrastive loss L_fc (ablation)DPPASS-T · DensePASS testmIoU: 42.40 -> 47.30; +4.90%Improved
combine all four losses rather than supervised loss alone (ablation)DPPASS-T · DensePASS testmIoU: 42.40 -> 55.30; +12.9Improved
use tangent projection size 224 × 224 rather than the tested alternatives (ablation)DPPASS-T · DensePASS testmIoU: 49.98, 52.22, 55.30, 55.17, 52.56Mixed
set alpha to 0.02 instead of the other tested values (ablation)DPPASS-T · DensePASS testmIoU: 48.25, 50.01, 50.12, 48.12, 47.44Mixed
set beta to 50 instead of the other tested values (ablation)DPPASS-T · DensePASS testmIoU: 46.97, 47.21, 49.53, 49.38, 42.1Mixed
use DPPASS-S instead of Trans4PASS-SSegformer-B2 · DensePASS testmIoU: 55.22 -> 56.28; +1.06%Improved
use DPPASS-T instead of Trans4PASS-TSegformer-B1 · WildPASS testmIoU(%): 54.67 -> 60.38; 5.71%Improved
use DPPASS-S instead of Trans4PASS-SSegformer-B2 · WildPASS testmIoU(%): 62.91 -> 63.53; 0.62%Improved

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