Papers › SIMPLE: Specialized Model-Sample Matching for Domain Generalization

SIMPLE: Specialized Model-Sample Matching for Domain Generalization

1 May 2023International Conference on Learning Representations 2023 5archive 2025-07-28

Ziyue Li, Kan Ren, Xinyang Jiang, Yifei Shen, Haipeng Zhang, Dongsheng Li

In domain generalization (DG), most existing methods aspire to fine-tune a specific pretrained model through novel DG algorithms. In this paper, we propose an alternative direction, i.e., to efficiently leverage a pool of pretrained models without fine-tuning. Through extensive empirical and theoretical evidence, we demonstrate that (1) pretrained models have possessed generalization to some extent while there is no single best pretrained model across all distribution shifts, and (2) out-of-distribution (OOD) generalization error depends on the fitness between the pretrained model and unseen test distributions. This analysis motivates us to incorporate diverse pretrained models and to dispatch the best matched models for each OOD sample by means of recommendation techniques. To this end, we propose SIMPLE, a specialized model-sample matching method for domain generalization. First, the predictions of pretrained models are adapted to the target domain by a linear label space transformation. A matching network aware of model specialty is then proposed to dynamically recommend proper pretrained models to predict each test sample. The experiments on DomainBed show that our method achieves significant performance improvements (up to 12.2% for individual dataset and 3.9% on average) compared to state-of-the-art (SOTA) methods and further achieves 6.1% gain via enlarging the pretrained model pool. Moreover, our method is highly efficient and achieves more than 1000 times training speedup compared to the conventional DG methods with fine-tuning a pretrained model. Code and supplemental materials are available at https://seqml.github.io/simple.

PaperPDFCode

Syntology This paper has no arXiv id in the archive, and this site joins papers to Syntology's graph by arXiv id, so this page does not say whether the graph holds it.

Code

microsoft/SeqML officialpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ContiFormer: Continuous-Time Transformer for Irregular Time Series Modeling (arXiv:2402.10635; that paper's own run record: 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

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

Tasks

Domain Generalizationmodel

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Generalization DomainNet SIMPLE+ Average Accuracy 61.9 #7 of 38 Archive leaderboard report
Domain Generalization DomainNet SIMPLE Average Accuracy 49.2 #23 of 38 Archive leaderboard report
Domain Generalization Office-Home SIMPLE+ Average Accuracy 87.7 #4 of 45 Archive leaderboard report
Domain Generalization Office-Home SIMPLE Average Accuracy 84.6 #8 of 45 Archive leaderboard report
Domain Generalization PACS SIMPLE+ Average Accuracy 99.0 #1 of 133 Archive leaderboard report
Domain Generalization PACS SIMPLE Average Accuracy 88.6 #27 of 133 Archive leaderboard report
Domain Generalization TerraIncognita SIMPLE+ Average Accuracy 59.0 #7 of 30 Archive leaderboard report
Domain Generalization TerraIncognita SIMPLE Average Accuracy 57.6 #9 of 30 Archive leaderboard report
Domain Generalization VLCS SIMPLE+ Average Accuracy 82.7 #8 of 37 Archive leaderboard report
Domain Generalization VLCS SIMPLE Average Accuracy 79.9 #20 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.

Methods

AWARETest

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