FSDR: Frequency Space Domain Randomization for Domain Generalization

Abstract

Domain generalization aims to learn a generalizable model from a known source domain for various unknown target domains. It has been studied widely by domain randomization that transfers source images to different styles in spatial space for learning domain-agnostic features. However, most existing randomization uses GANs that often lack of controls and even alter semantic structures of images undesirably. Inspired by the idea of JPEG that converts spatial images into multiple frequency components (FCs), we propose Frequency Space Domain Randomization (FSDR) that randomizes images in frequency space by keeping domain-invariant FCs (DIFs) and randomizing domain-variant FCs (DVFs) only. FSDR has two unique features: 1) it decomposes images into DIFs and DVFs which allows explicit access and manipulation of them and more controllable randomization; 2) it has minimal effects on semantic structures of images and domain-invariant features. We examined domain variance and invariance property of FCs statistically and designed a network that can identify and fuse DIFs and DVFs dynamically through iterative learning. Extensive experiments over multiple domain generalizable segmentation tasks show that FSDR achieves superior segmentation and its performance is even on par with domain adaptation methods that access target data in training.

arXiv commentAccepted to CVPR2021

References in corpus (14)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
• Unsupervised Domain Adaptation with Residual Transfer Networks
• Understanding deep learning requires rethinking generalization
• FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
• Domain Generalization via Invariant Feature Representation
• Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes
• Domain Generalization via Model-Agnostic Learning of Semantic Features
• Generalizing Across Domains via Cross-Gradient Training
• Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks
• Learning to Generalize: Meta-Learning for Domain Generalization
• Adversarial Dropout Regularization
• Memory Warps for Learning Long-Term Online Video Representations
• Contextual-Relation Consistent Domain Adaptation for Semantic Segmentation

Cited by in corpus (5)

• MLAN: Multi-Level Adversarial Network for Domain Adaptive Semantic Segmentation
• Category Contrast for Unsupervised Domain Adaptation in Visual Tasks
• Semi-Supervised Domain Adaptation via Adaptive and Progressive Feature Alignment
• Cross-domain Transfer of defect features in technical domains based on partial target data
• Spectral Unsupervised Domain Adaptation for Visual Recognition