The reviewed record of science sign in
Pith

arxiv: 2207.12020 · v2 · pith:EHZFG66N · submitted 2022-07-25 · cs.LG · cs.CV

Domain-invariant Feature Exploration for Domain Generalization

Reviewed by Pithpith:EHZFG66Nopen to challenge →

classification cs.LG cs.CV
keywords featuresdomaindomain-invariantdifexdomainsexplorationfeaturegeneralization
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.