AI Paper Atlas

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

mDALU: Multi-Source Domain Adaptation and Label Unification With Partial Datasets

Rui Gong, Dengxin Dai, Yuhua Chen, Wen Li, Luc Van Gool

ICCV 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 23 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 multi-branch network (MBR) (ablation)source-only baseline · Digits classification, non-overlapping source labels (avg of MT/SYN/SVHN targets)accuracy (%): 60.65 -> 61.62Improved
add uncertainty maximization (UM) (ablation)MBR · Digits classification, non-overlapping source labels (avg of MT/SYN/SVHN targets)accuracy (%): 61.62 -> 73.08Improved
add the A3 module's domain attention (DAT, no adversarial part) (ablation)MBR + UM · Digits classification, non-overlapping source labels (avg of MT/SYN/SVHN targets)accuracy (%): 73.08 -> 74.90Improved
add adversarial alignment to A3 (ablation)MBR + UM + DAT · Digits classification, non-overlapping source labels (avg of MT/SYN/SVHN targets)accuracy (%): 74.90 -> 75.13Improved
add pseudo-label supervision fusion (PSF) (ablation)mDALU w/o PSF · Digits classification, non-overlapping source labels (avg of MT/SYN/SVHN targets)accuracy (%): 75.13 -> 79.00Improved
apply domain adaptation methods DANN/DCTN/M3SDA without label unificationsource-only · Digits classification, non-overlapping source labels (avg of MT/SYN/SVHN targets)accuracy (%): 60.65 -> 59.75Hurt
use ambiguity cross entropy label unification (AENT)source-only · Digits classification, non-overlapping source labels (avg of MT/SYN/SVHN targets)accuracy (%): 60.65 -> 64.90Improved
add PSF (ablation)mDALU w/o PSF · Digits, 4 source domains (avg)accuracy (%): 80.83 -> 82.88Improved
add PSF (ablation)mDALU w/o PSF · Cross-modal 2D (Cityscapes+Nuscenes->A2D2)mIoU (%): 38.1 -> 54.9Improved
add PSF (ablation)mDALU w/o PSF · Cross-modal 3D (Cityscapes+Nuscenes->A2D2)mIoU (%): 2.4 -> 37.1Improved
add inference weight map for inconsistent taxonomies (ablation)Ours w/o PSF · GTA5+SYNTHIA->Cityscapes (T, inconsistent taxonomies)mIoU (%): 35.3 -> 37.2Improved
add PSF with relabeling of inconsistent classes (ablation)Ours (PSF w/o relabeling) · GTA5+SYNTHIA->Cityscapes (T, inconsistent taxonomies)mIoU (%): 38.4 -> 40.0Improved

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