Papers › Adaptive Methods for Aggregated Domain Generalization
Adaptive Methods for Aggregated Domain Generalization
Xavier Thomas, Dhruv Mahajan, Alex Pentland, Abhimanyu Dubey
Domain generalization involves learning a classifier from a heterogeneous collection of training sources such that it generalizes to data drawn from similar unknown target domains, with applications in large-scale learning and personalized inference. In many settings, privacy concerns prohibit obtaining domain labels for the training data samples, and instead only have an aggregated collection of training points. Existing approaches that utilize domain labels to create domain-invariant feature representations are inapplicable in this setting, requiring alternative approaches to learn generalizable classifiers. In this paper, we propose a domain-adaptive approach to this problem, which operates in two steps: (a) we cluster training data within a carefully chosen feature space to create pseudo-domains, and (b) using these pseudo-domains we learn a domain-adaptive classifier that makes predictions using information about both the input and the pseudo-domain it belongs to. Our approach achieves state-of-the-art performance on a variety of domain generalization benchmarks without using domain labels whatsoever. Furthermore, we provide novel theoretical guarantees on domain generalization using cluster information. Our approach is amenable to ensemble-based methods and provides substantial gains even on large-scale benchmark datasets. The code can be found at: https://github.com/xavierohan/AdaClust_DomainBed
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Domain Generalization | DomainNet | AdaClust (ResNet-50, SWAD) | Average Accuracy | 46.7 | #29 of 38 | Archive leaderboard | report |
| Domain Generalization | DomainNet | AdaClust (ResNet-50) | Average Accuracy | 43.3 | #37 of 38 | Archive leaderboard | report |
| Domain Generalization | Office-Home | AdaClust (ResNet-50, SWAD) | Average Accuracy | 69.4 | #34 of 45 | Archive leaderboard | report |
| Domain Generalization | Office-Home | AdaClust (ResNet-50) | Average Accuracy | 67.7 | #37 of 45 | Archive leaderboard | report |
| Domain Generalization | PACS | AdaClust (ResNet-50, SWAD) | Average Accuracy | 89.2 | #22 of 133 | Archive leaderboard | report |
| Domain Generalization | PACS | AdaClust (ResNet-50) | Average Accuracy | 87.0 | #40 of 133 | Archive leaderboard | report |
| Domain Generalization | TerraIncognita | AdaClust (ResNet-50, SWAD) | Average Accuracy | 50.6 | #23 of 30 | Archive leaderboard | report |
| Domain Generalization | TerraIncognita | AdaClust (ResNet-50) | Average Accuracy | 48.1 | #29 of 30 | Archive leaderboard | report |
| Domain Generalization | VLCS | AdaClust (ResNet-50, SWAD) | Average Accuracy | 79.6 | #23 of 37 | Archive leaderboard | report |
| Domain Generalization | VLCS | AdaClust (ResNet-50) | Average Accuracy | 78.9 | #32 of 37 | 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