AI Paper Atlas

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

Dual Path Learning for Domain Adaptation of Semantic Segmentation

Yiting Cheng, Fangyun Wei, Jianmin Bao, Dong Chen, Fang Wen, Wenqiang Zhang

ICCV 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 79 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 dual perceptual loss (DPIT) instead of single path perceptual loss (ablation)image translation, M_T mIoU · GTA5->Cityscapes ablation (first iteration)mIoU: 51.1 -> 51.8Improved
add perceptual loss to CycleGAN translation (SPIT) (ablation)image translation, M_T mIoU · GTA5->Cityscapes ablation (first iteration)mIoU: 48.5 -> 51.1Improved
use dual path pseudo labels (weighted) instead of single path (ablation)pseudo label generation, M_T mIoU · GTA5->Cityscapes ablation (first iteration)mIoU: 50.0 -> 51.8Improved
weighted averaging instead of max of two paths (ablation)DPPLG, M_T mIoU · GTA5->Cityscapes ablation (first iteration)mIoU: 50.6 -> 51.8Improved
weighted averaging instead of intersecting pseudo labels (ablation)DPPLG, M_T mIoU · GTA5->Cityscapes ablation (first iteration)mIoU: 50.3 -> 51.8Improved
add label correction versus raw ground-truth labels for M_T warm-up (ablation)M_T warm-up · GTA5->Cityscapes (warm-up)mIoU: 46.2 -> 48.5Improved
add label correction versus raw pseudo labels for M_T warm-up (ablation)M_T warm-up · GTA5->Cityscapes (warm-up)mIoU: 44.3 -> 48.5Improved
add M_T warm-up strategy (ablation)DPL ResNet101 · GTA5->Cityscapes valmIoU: 49.0 -> 52.8Improved
run first DPAS iteration after warm-up (ablation)M_T · GTA5->Cityscapes ablation (first iteration)mIoU: 48.5 -> 51.8Improved
separate segmentation models instead of sharing all weights (ablation)M_S and M_T · GTA5->Cityscapes ablation (first iteration)mIoU: 49.2 -> 51.8Improved
separate segmentation models instead of sharing first 4 blocks (ablation)M_S and M_T · GTA5->Cityscapes ablation (first iteration)mIoU: 49.6 -> 51.8Improved
use alpha 0.5 instead of only target path (alpha 1) (ablation)pseudo label weighting · GTA5->Cityscapes ablation (first iteration)mIoU: 50.0 -> 51.8Improved

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