A Fourier-based Framework for Domain Generalization
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.
Code (1)
Tasks
Data AugmentationDomain GeneralizationSimilar Papers 제목 키워드 기반
Domain Generalization with Fourier Transform and Soft Thresholding
Domain generalization aims to train models on multiple source domains so that they can generalize well to unseen target domains. Among many domain generalization methods, Fourier-transform-based domain generalization met…
Domain GeneralizationImage AugmentationImage SegmentationSemantic SegmentationFourier-Attentive Representation Learning: A Fourier-Guided Framework for Few-Shot Generalization in Vision-Language Models
Large-scale pre-trained Vision-Language Models (VLMs) have demonstrated strong few-shot learning capabilities. However, these methods typically learn holistic representations where an image's domain-invariant structure i…
Representation LearningFew-Shot LearningSemantic-Aware Mixup for Domain Generalization
Deep neural networks (DNNs) have shown exciting performance in various tasks, yet suffer generalization failures when meeting unknown target domains. One of the most promising approaches to achieve domain generalization …
Domain Generalizationimage-classificationImage ClassificationFOUND: Fourier-based von Mises Distribution for Robust Single Domain Generalization in Object Detection
Single Domain Generalization (SDG) for object detection aims to train a model on a single source domain that can generalize effectively to unseen target domains. While recent methods like CLIP-based semantic augmentation…
Domain GeneralizationObject DetectionClifford Fourier-Mellin transform with two real square roots of -1 in Cl(p,q), p+q=2
We describe a non-commutative generalization of the complex Fourier-Mellin transform to Clifford algebra valued signal functions over the domain $\R^{p,q}$ taking values in Cl(p,q), p+q=2. Keywords: algebra, Fourier tr…