AI Paper Atlas

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

DaDA: Distortion-aware Domain Adaptation for Unsupervised Semantic Segmentation

Sujin Jang, Joohan Na, Dokwan Oh

NeurIPS 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 1 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 RA+RDL distortion-aware transformationAdvEnt · Cityscapes->WoodscapemIoU (%): 45.26 -> 52.64Improved
add RA+RDL distortion-aware transformationAdaptSeg · Cityscapes->WoodscapemIoU (%): 46.33 -> 52.59Improved
add RA+RDL distortion-aware transformationAdvEnt · GTAV->WoodscapemIoU (%): 34.70 -> 37.62Improved
add RA+RDL distortion-aware transformationAdvEnt · GTAV->FDDmIoU (%): 37.25 -> 40.87Improved
add only RandAugment affine transformation (ablation)AdaptSeg · GTAV->WoodscapemIoU (%): 35.94 -> 36.88Improved
add only diffeomorphic RDL (ablation)AdaptSeg · Cityscapes->FDDmIoU (%): 39.07 -> 41.35Improved
add RA on top of RDL (ablation)AdaptSeg+RDL · Cityscapes->FDDmIoU (%): 41.35 -> 41.07Hurt
add RA on top of RDL (ablation)AdvEnt+RDL · Cityscapes->FDDmIoU (%): 42.43 -> 42.32Hurt
add RA on top of RDL (ablation)AdvEnt+RDL · GTAV->WoodscapemIoU (%): 36.39 -> 37.62Improved
use DaDA as warm-up for IASTIAST · Cityscapes->WoodscapemIoU (%): 47.00 -> 53.82Improved
use DaDA as warm-up for IntraDAIntraDA · GTAV->WoodscapemIoU (%): 36.10 -> 39.85Improved
use DaDA as warm-up for ProDAProDA · GTAV->FDDmIoU (%): 35.97 -> 37.09Improved

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