A Fourier-based Framework for Domain Generalization
This addresses performance degradation in AI models when faced with unseen data distributions, though it is incremental as it builds on existing domain generalization methods.
The paper tackles the problem of domain generalization in deep neural networks by introducing a Fourier-based framework that uses amplitude mix augmentation and co-teacher regularization, achieving state-of-the-art performance on three benchmarks.
Modern deep neural networks suffer from performance degradation when evaluated on testing data under different distributions from training data. Domain generalization aims at tackling this problem by learning transferable knowledge from multiple source domains in order to generalize to unseen target domains. This paper introduces a novel Fourier-based perspective for domain generalization. The main assumption is that the Fourier phase information contains high-level semantics and is not easily affected by domain shifts. To force the model to capture phase information, we develop a novel Fourier-based data augmentation strategy called amplitude mix which linearly interpolates between the amplitude spectrums of two images. A dual-formed consistency loss called co-teacher regularization is further introduced between the predictions induced from original and augmented images. Extensive experiments on three benchmarks have demonstrated that the proposed method is able to achieve state-of-the-arts performance for domain generalization.