Papers › Implicit Class-Conditioned Domain Alignment for Unsupervised Domain Adaptation

Implicit Class-Conditioned Domain Alignment for Unsupervised Domain Adaptation

9 Jun 2020ICML 2020 1arXiv:2006.04996archive 2025-07-28

Xiang Jiang, Qicheng Lao, Stan Matwin, Mohammad Havaei

We present an approach for unsupervised domain adaptation---with a strong focus on practical considerations of within-domain class imbalance and between-domain class distribution shift---from a class-conditioned domain alignment perspective. Current methods for class-conditioned domain alignment aim to explicitly minimize a loss function based on pseudo-label estimations of the target domain. However, these methods suffer from pseudo-label bias in the form of error accumulation. We propose a method that removes the need for explicit optimization of model parameters from pseudo-labels directly. Instead, we present a sampling-based implicit alignment approach, where the sample selection procedure is implicitly guided by the pseudo-labels. Theoretical analysis reveals the existence of a domain-discriminator shortcut in misaligned classes, which is addressed by the proposed implicit alignment approach to facilitate domain-adversarial learning. Empirical results and ablation studies confirm the effectiveness of the proposed approach, especially in the presence of within-domain class imbalance and between-domain class distribution shift.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

xiangdal/implicit_alignment officialmentioned in papermentioned on GitHubpytorchNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Domain AdaptationPseudo LabelUnsupervised Domain Adaptation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Domain Adaptation Office-31 Implicit Alignment (with MDD) Avg accuracy 88.8 #5 of 5 Archive leaderboard report
Unsupervised Domain Adaptation Office-Home Implicit Alignment (with MDD) Avg accuracy 69.5 #19 of 20 Archive leaderboard report
Unsupervised Domain Adaptation Office-Home (RS-UT imbalance) Implicit Alignment (with MDD) Average Per-Class Accuracy 61.67 #1 of 5 Archive leaderboard report
Unsupervised Domain Adaptation Office-Home (RS-UT imbalance) COAL Average Per-Class Accuracy 58.4 #2 of 5 Archive leaderboard report
Unsupervised Domain Adaptation Office-Home (RS-UT imbalance) DANN Average Per-Class Accuracy 56.91 #3 of 5 Archive leaderboard report
Unsupervised Domain Adaptation Office-Home (RS-UT imbalance) MDD Average Per-Class Accuracy 55.44 #4 of 5 Archive leaderboard report
Unsupervised Domain Adaptation Office-Home (RS-UT imbalance) Source Only Average Per-Class Accuracy 52.81 #5 of 5 Archive leaderboard report
Unsupervised Domain Adaptation VisDA2017 Implicit Alignment (with MDD) Accuracy 75.8 #11 of 13 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections