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

In real-world scenarios, achieving domain generalization (DG) presentssignificant challenges as models are required to generalize to unknown targetdistributions. Generalizing to unseen multi-modal distributions poses evengreater difficulties due to the distinct properties exhibited by differentmodalities. To overcome the challenges of achieving domain generalization inmulti-modal scenarios, we propose SimMMDG, a simple yet effective multi-modalDG framework. We argue that mapping features from different modalities into thesame embedding space impedes model generalization. To address this, we proposesplitting the features within each modality into modality-specific andmodality-shared components. We employ supervised contrastive learning on themodality-shared features to ensure they possess joint properties and imposedistance constraints on modality-specific features to promote diversity. Inaddition, we introduce a cross-modal translation module to regularize thelearned features, which can also be used for missing-modality generalization.We demonstrate that our framework is theoretically well-supported and achievesstrong performance in multi-modal DG on the EPIC-Kitchens dataset and the novelHuman-Animal-Cartoon (HAC) dataset introduced in this paper. Our source codeand HAC dataset are available at https://github.com/donghao51/SimMMDG.

SimMMDG: A Simple and Effective Framework for Multi-modal Domain Generalization