The artistic style within a painting is the means of expression, which includes not only the
painting material, colors, and brushstrokes, but also the high-level attributes, including …

Content and style (CS) disentanglement is a fundamental problem and critical challenge of
style transfer. Existing approaches based on explicit definitions (eg, Gram matrix) or implicit …

Abstract Single Domain Generalization (SDG) tackles the problem of training a model on a
single source domain so that it generalizes to any unseen target domain. While this has …

This paper presents a simple yet effective approach that improves continual test-time
adaptation (TTA) in a memory-efficient manner. TTA may primarily be conducted on edge …

Despite the remarkable performance that modern deep neural networks have achieved on
independent and identically distributed (IID) data, they can crash under distribution shifts …

Abstract Domain generalization (DG) aims to improve the generalization performance for an
unseen target domain by using the knowledge of multiple seen source domains. Mainstream …

Abstract Deep Neural Networks have exhibited considerable success in various visual tasks.
However, when applied to unseen test datasets, state-of-the-art models often suffer …

With the emergence of pre-trained vision-language models like CLIP how to adapt them to
various downstream classification tasks has garnered significant attention in recent …

The mechanism of existing style transfer algorithms is by minimizing a hybrid loss function to
push the generated image toward high similarities in both content and style. However, this …

Abstract Domain generalization (DG) aims to learn a model that generalizes well to unseen
target domains utilizing multiple source domains without re-training. Most existing DG works …