AI Paper Atlas

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

Behind Every Domain There is a Shift: Adapting Distortion-Aware Vision Transformers for Panoramic Semantic Segmentation

Jiaming Zhang, Kailun Yang, Hao Shi, Simon Reiß, Kunyu Peng, Chaoxiang Ma, Haodong Fu, Philip H. S. Torr, Kaiwei Wang, Rainer Stiefelhagen

TPAMI 2024 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 56 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 deformable patch embedding (DPE) (ablation)Trans4PASS+ baseline · DensePASS (Cityscapes 512x512)mIoU: 39.02 -> 43.11Improved
add DMLPv2 on top of DPE (ablation)Trans4PASS+ · DensePASS (Cityscapes 512x512)mIoU: 43.11 -> 49.94Improved
use DMLPv2 instead of DMLPv1 with DPE (ablation)Trans4PASS+ · DensePASS (Cityscapes 512x512)mIoU: 45.89 -> 49.94Improved
add DMLPv1 on top of DPE (ablation)Trans4PASS+ · DensePASS (Cityscapes 512x512)mIoU: 43.11 -> 45.89Improved
add DMLPv2 (channel mixer) alongside pooling mixer (ablation)DMLPv2 · DensePASS (Cityscapes 512x512)mIoU: 46.66 -> 49.94Improved
add pooling mixer alongside channel mixer (ablation)DMLPv2 · DensePASS (Cityscapes 512x512)mIoU: 47.66 -> 49.94Improved
use DMLPv2 instead of PoolFormer+FAN token mixing (ablation)Trans4PASS+ · DensePASS (Cityscapes 512x512)mIoU: 45.97 -> 49.94Improved
use DMLPv2 instead of CycleMLP (ablation)Trans4PASS+ with DPE · DensePASS (Cityscapes 512x512)mIoU: 40.16 -> 49.94Improved
use DPE instead of vanilla patch embedding with DMLPv2 (ablation)Trans4PASS+ · DensePASS (Cityscapes 512x512)mIoU: 47.08 -> 49.94Improved
use DMLPv2 instead of vanilla MLP: Cityscapes accuracy cost (ablation)Trans4PASS+ · Cityscapes val (Cityscapes 512x512)mIoU: 74.93 -> 65.86Hurt
replace SSL pseudo labels with SAM-rectified labels plus MPATrans4PASS+ (S) · DensePASS UDAmIoU: 56.38 -> 59.43Improved
upgrade Trans4PASS to Trans4PASS+ (Small)Trans4PASS · SynPASS testmIoU: 38.57 -> 40.72Improved

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