Abstract Machine learning methods strive to acquire a robust model during the training
process that can effectively generalize to test samples, even in the presence of distribution …

The goal of semantic segmentation is to segment the input image according to semantic
information and predict the semantic category of each pixel from a given label set. With the …

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 …

The goal of image style transfer is to render an image with artistic features guided by a style
reference while maintaining the original content. Owing to the locality in convolutional neural …

Objective measures of image quality generally operate by comparing pixels of a “degraded”
image to those of the original. Relative to human observers, these measures are overly …

Pre-trained large text-to-image models synthesize impressive images with an appropriate
use of text prompts. However, ambiguities inherent in natural language, and out-of …

Universal style transfer retains styles from reference images in content images. While
existing methods have achieved state-of-the-art style transfer performance, they are not …

This paper studies domain generalization via domain-invariant representation learning.
Existing methods in this direction suppose that a domain can be characterized by styles of its …

Deep domain adaptation has emerged as a new learning technique to address the lack of
massive amounts of labeled data. Compared to conventional methods, which learn shared …

We present a simple and general method to train a single neural network executable at
different widths (number of channels in a layer), permitting instant and adaptive accuracy …