Papers › Learning to Balance Specificity and Invariance for In and Out of Domain Generalization

Learning to Balance Specificity and Invariance for In and Out of Domain Generalization

28 Aug 2020ECCV 2020 8arXiv:2008.12839archive 2025-07-28

Prithvijit Chattopadhyay, Yogesh Balaji, Judy Hoffman

We introduce Domain-specific Masks for Generalization, a model for improving both in-domain and out-of-domain generalization performance. For domain generalization, the goal is to learn from a set of source domains to produce a single model that will best generalize to an unseen target domain. As such, many prior approaches focus on learning representations which persist across all source domains with the assumption that these domain agnostic representations will generalize well. However, often individual domains contain characteristics which are unique and when leveraged can significantly aid in-domain recognition performance. To produce a model which best generalizes to both seen and unseen domains, we propose learning domain specific masks. The masks are encouraged to learn a balance of domain-invariant and domain-specific features, thus enabling a model which can benefit from the predictive power of specialized features while retaining the universal applicability of domain-invariant features. We demonstrate competitive performance compared to naive baselines and state-of-the-art methods on both PACS and DomainNet.

PaperPDFConference PDFCode

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

Code

prithv1/DMG officialmentioned in paperpytorchMIT 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 GeneralizationSpecificity

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Generalization DomainNet DMG (ResNet-50) Average Accuracy 43.63 #35 of 38 Archive leaderboard report
Domain Generalization DomainNet MetaReg (ResNet-50) Average Accuracy 43.62 #36 of 38 Archive leaderboard report
Domain Generalization PACS DMG (Resnet-50) Average Accuracy 83.37 #69 of 133 Archive leaderboard report
Domain Generalization PACS DMG (Resnet-18) Average Accuracy 81.46 #87 of 133 Archive leaderboard report
Domain Generalization PACS DMG (Alexnet) Average Accuracy 73.32 #111 of 133 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