English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Large-scale foundation models, such as CLIP, have demonstrated impressivezero-shot generalization performance on downstream tasks, leveragingwell-designed language prompts. However, these prompt learning techniques oftenstruggle with domain shift, limiting their generalization capabilities. In ourstudy, we tackle this issue by proposing StyLIP, a novel approach for DomainGeneralization (DG) that enhances CLIP's classification performance acrossdomains. Our method focuses on a domain-agnostic prompt learning strategy,aiming to disentangle the visual style and content information embedded inCLIP's pre-trained vision encoder, enabling effortless adaptation to noveldomains during inference. To achieve this, we introduce a set of styleprojectors that directly learn the domain-specific prompt tokens from theextracted multi-scale style features. These generated prompt embeddings aresubsequently combined with the multi-scale visual content features learned by acontent projector. The projectors are trained in a contrastive manner,utilizing CLIP's fixed vision and text backbones. Through extensive experimentsconducted in five different DG settings on multiple benchmark datasets, weconsistently demonstrate that StyLIP outperforms the current state-of-the-art(SOTA) methods.

StyLIP: Multi-Scale Style-Conditioned Prompt Learning for CLIP-based Domain Generalization