AI Paper Atlas

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

Look at the Neighbor: Distortion-aware Unsupervised Domain Adaptation for Panoramic Semantic Segmentation

Xu Zheng, Tianbo Pan, Yunhao Luo, Lin Wang

ICCV 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 29 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 distortion-aware attention in the deepest layer (after ESA layers) (ablation)DATR-M · Cityscapes-to-DensePASS (source only)mIoU: 36.45 -> 38.48Improved
add DA in the shallow layers (ablation)DATR-M · Cityscapes-to-DensePASS (source only)mIoU: 36.45 -> 37.56No clear effect
use relative positional encoding instead of absolute positional encoding (ablation)DATR-M · SynPASS-to-DensePASS13mIoU: 41.56 -> 51.04Improved
add relative positional encoding versus none (ablation)DATR-M · SynPASS-to-DensePASS13mIoU: 36.98 -> 51.04Improved
add class-wise feature aggregation on top of pseudo-label self-training (ablation)DATR-M · Cityscapes-to-DensePASSmIoU: 45.71 -> 52.90Improved
add CFA on top of self-training (ablation)DATR-S · SynPASS-to-DensePASS13mIoU: 50.08 -> 54.05Improved
replace MPA with CFA (ablation)DATR-M/T/S · SynPASS-to-DensePASS13mIoU: 48.24 -> 51.04Improved
replace non-iterative or linear class-center update with iterative update (ablation)CFA · SynPASS-to-DensePASS13 (DATR-M)mIoU: 50.43 / 50.53 -> 51.04Improved
use DATR backbones instead of PVT-S under MPAMPA · SynPASS-to-DensePASS13mIoU: 40.90 -> 52.76Improved
compact DATR-M versus Trans4PASS-S backbone without adaptation on Cityscapes-trained modelsDATR-M · Cityscapes (CS) mIoUmIoU on Cityscapes: 81.17 -> 75.23Hurt
change neighborhood region size of DA away from 11x11DATR-M · DensePASS testmIoUHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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