Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalization
Preprint
Abstract
Arbitrary style transfer (AST) and domain generalization (DG) are important yet challenging visual learning tasks, which can be cast as a feature distribution matching problem. With the assumption of Gaussian feature distribution, conventional feature distribution matching methods usually match the mean and standard deviation of features. However, the feature distributions of real-world data are usually much more complicated than Gaussian, which cannot be accurately matched by using only the first-order and second-order statistics, while it is computationally prohibitive to use high-order statistics for distribution matching. In this work, we, for the first time to our best knowledge, propose to perform Exact Feature Distribution Matching (EFDM) by exactly matching the empirical Cumulative Distribution Functions (eCDFs) of image features, which could be implemented by applying the Exact Histogram Matching (EHM) in the image feature space. Particularly, a fast EHM algorithm, named Sort-Matching, is employed to perform EFDM in a plug-and-play manner with minimal cost. The effectiveness of our proposed EFDM method is verified on a variety of AST and DG tasks, demonstrating new state-of-the-art results. Codes are available at https://github.com/YBZh/EFDM.Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- Generalizing to Unseen Domains: A Survey on Domain Generalization2021
- Unsupervised Multi-Class Domain Adaptation: Theory, Algorithms, and PracticeIEEE Transactions on Pattern Analysis and Machine Intelligence, 2020
- Demystifying Neural Style Transfer2017
- Exact histogram specificationIEEE Transactions on Image Processing, 2006
- Almost Uniform Distributions for Computer Image EnhancementIEEE Transactions on Computers, 1974
- Sequential Operations in Digital Picture ProcessingJournal of the ACM, 1966