Unknown Domain Inconsistency Minimization for Domain Generalization
The objective of domain generalization (DG) is to enhance the transferability of the model learned from a source domain to unobserved domains. To prevent overfitting to a specific domain, Sharpness-Aware Minimization (SAM) reduces source domain's loss sharpness. Although SAM variants have delivered significant improvements in DG, we highlight that there's still potential for improvement in generalizing to unknown domains through the exploration on data space. This paper introduces an objective rooted in both parameter and data perturbed regions for domain generalization, coined Unknown Domain Inconsistency Minimization (UDIM). UDIM reduces the loss landscape inconsistency between source domain and unknown domains. As unknown domains are inaccessible, these domains are empirically crafted by perturbing instances from the source domain dataset. In particular, by aligning the loss landscape acquired in the source domain to the loss landscape of perturbed domains, we expect to achieve generalization grounded on these flat minima for the unknown domains. Theoretically, we validate that merging SAM optimization with the UDIM objective establishes an upper bound for the true objective of the DG task. In an empirical aspect, UDIM consistently outperforms SAM variants across multiple DG benchmark datasets. Notably, UDIM shows statistically significant improvements in scenarios with more restrictive domain information, underscoring UDIM's generalization capability in unseen domains. Our code is available at \url{https://github.com/SJShin-AI/UDIM}.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain GeneralizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Inconsistency-Aware Minimization: Improving Generalization with Unlabeled Data
Estimating the generalization gap and developing optimization methods that improve generalization are crucial for deep learning models, for both theoretical understanding and practical applications. Leveraging unlabeled …
Self-Supervised LearningDomain-Specific Risk Minimization for Out-of-Distribution Generalization
Recent domain generalization (DG) approaches typically use the hypothesis learned on source domains for inference on the unseen target domain. However, such a hypothesis can be arbitrarily far from the optimal one for th…
Domain AdaptationDomain GeneralizationOut-of-Distribution GeneralizationFlatness-Aware Minimization for Domain Generalization
Domain generalization (DG) seeks to learn robust models that generalize well under unknown distribution shifts. As a critical aspect of DG, optimizer selection has not been explored in depth. Currently, most DG methods f…
Domain GeneralizationFADSeeking Consistent Flat Minima for Better Domain Generalization via Refining Loss Landscapes
Domain generalization aims to learn a model from multiple training domains and generalize it to unseen test domains. Recent theory has shown that seeking the deep models, whose parameters lie in the flat minima of the lo…
Domain GeneralizationUnsupervised Open Domain Recognition by Semantic Discrepancy Minimization
We address the unsupervised open domain recognition (UODR) problem, where categories in labeled source domain S is only a subset of those in unlabeled target domain T. The task is to correctly classify all samples in T i…
ClassificationGeneral Classification