FSDR: Frequency Space Domain Randomization for Domain Generalization

By Jiaxing Huang, Dayan Guan, Aoran Xiao, Shijian Lu. Computer Vision and Pattern Recognition, 2021

308 citations recorded by the source corpus.

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 methods use 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.

Subfields: Artificial Intelligence, Cancer Research, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/943f0e5a21afc1d576d08aa40f93cea8d51f2bbe

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Tao Qin
2. Jindong Wang
3. Yidong Ouyang
4. Chang Liu
5. Cuiling Lan
6. Tie-Yan Liu
7. Xu Tan
8. Sheng Zhao

In Cancer Research

1. Jindong Wang
2. Cuiling Lan

In Computer Vision and Pattern Recognition

1. Tao Qin
2. Jindong Wang
3. Yidong Ouyang
4. Chang Liu
5. Cuiling Lan
6. Tie-Yan Liu
7. Xu Tan
8. Jun Liu

Citations in the corpus

• Generalizing to Unseen Domains: A Survey on Domain Generalization (2021, methodology): “adopted the regularization of weak and strong augmentation in [31], [170].”