Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalization

03/15/2022
by   Yabin Zhang, et al.
0

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.

READ FULL TEXT

page 6

page 8

research
05/19/2022

Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learning

In this work, we tackle the challenging problem of arbitrary image style...
research
06/26/2022

Non-Parametric Style Transfer

Recent feed-forward neural methods of arbitrary image style transfer mai...
research
01/04/2017

Demystifying Neural Style Transfer

Neural Style Transfer has recently demonstrated very exciting results wh...
research
03/12/2021

In the light of feature distributions: moment matching for Neural Style Transfer

Style transfer aims to render the content of a given image in the graphi...
research
08/08/2021

AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer

Fast arbitrary neural style transfer has attracted widespread attention ...
research
12/27/2019

HoMM: Higher-order Moment Matching for Unsupervised Domain Adaptation

Minimizing the discrepancy of feature distributions between different do...
research
04/20/2021

Gradient Matching for Domain Generalization

Machine learning systems typically assume that the distributions of trai...

Please sign up or login with your details

Forgot password? Click here to reset