Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Domain-invariant Feature Exploration for Domain Generalization

About

Deep learning has achieved great success in the past few years. However, the performance of deep learning is likely to impede in face of non-IID situations. Domain generalization (DG) enables a model to generalize to an unseen test distribution, i.e., to learn domain-invariant representations. In this paper, we argue that domain-invariant features should be originating from both internal and mutual sides. Internal invariance means that the features can be learned with a single domain and the features capture intrinsic semantics of data, i.e., the property within a domain, which is agnostic to other domains. Mutual invariance means that the features can be learned with multiple domains (cross-domain) and the features contain common information, i.e., the transferable features w.r.t. other domains. We then propose DIFEX for Domain-Invariant Feature EXploration. DIFEX employs a knowledge distillation framework to capture the high-level Fourier phase as the internally-invariant features and learn cross-domain correlation alignment as the mutually-invariant features. We further design an exploration loss to increase the feature diversity for better generalization. Extensive experiments on both time-series and visual benchmarks demonstrate that the proposed DIFEX achieves state-of-the-art performance.

Wang Lu, Jindong Wang, Haoliang Li, Yiqiang Chen, Xing Xie• 2022

Related benchmarks

TaskDatasetResultRank
Open Domain GeneralizationMulti-Datasets Sketch (test)
Accuracy27.45
12
Image ClassificationOffice-Home Art Open Domain Setting
Accuracy40.67
12
Image ClassificationOffice-Home Clipart Open Domain Setting
Accuracy44.2
12
Image ClassificationOffice-Home Real World Open Domain Setting
Accuracy60.75
12
Image ClassificationOffice-Home Open Domain Setting (Average)
Acc49.62
12
Open Domain GeneralizationMulti-Datasets Clipart (test)
Accuracy30.27
12
Open Domain GeneralizationMulti-Datasets Real (test)
Accuracy60.13
12
Open Domain GeneralizationMulti-Datasets Avg (test)
Accuracy39.08
12
Image ClassificationOffice-Home Product Open Domain Setting
Accuracy52.86
12
Image ClassificationPACS Open Domain (test)
Accuracy (Art)46.24
12
Showing 10 of 11 rows

Other info

Follow for update