all AI news
CLAP: Isolating Content from Style through Contrastive Learning with Augmented Prompts
March 12, 2024, 4:49 a.m. | Yichao Cai, Yuhang Liu, Zhen Zhang, Javen Qinfeng Shi
cs.CV updates on arXiv.org arxiv.org
Abstract: Contrastive vision-language models, such as CLIP, have garnered considerable attention for various dowmsteam tasks, mainly due to the remarkable ability of the learned features for generalization. However, the features they learned often blend content and style information, which somewhat limits their generalization capabilities under distribution shifts. To address this limitation, we adopt a causal generative perspective for multimodal data and propose contrastive learning with data augmentation to disentangle content features from the original representations. To …
abstract arxiv attention blend capabilities clap clip cs.cv features however information language language models prompts style tasks through type vision vision-language models
More from arxiv.org / cs.CV updates on arXiv.org
Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs
1 day, 10 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Principal Applied Scientist
@ Microsoft | Redmond, Washington, United States
Data Analyst / Action Officer
@ OASYS, INC. | OASYS, INC., Pratt Avenue Northwest, Huntsville, AL, United States