all AI news
Understanding the Robustness of Multi-modal Contrastive Learning to Distribution Shift
March 19, 2024, 4:44 a.m. | Yihao Xue, Siddharth Joshi, Dang Nguyen, Baharan Mirzasoleiman
cs.LG updates on arXiv.org arxiv.org
Abstract: Recently, multimodal contrastive learning (MMCL) approaches, such as CLIP, have achieved a remarkable success in learning representations that are robust against distribution shift and generalize to new domains. Despite the empirical success, the mechanism behind learning such generalizable representations is not understood. In this work, we rigorously analyze this problem and uncover two mechanisms behind MMCL's robustness: \emph{intra-class contrasting}, which allows the model to learn features with a high variance, and \emph{inter-class feature sharing}, where …
abstract arxiv clip cs.lg distribution domains modal multi-modal multimodal robust robustness shift success type understanding work
More from arxiv.org / cs.LG updates on 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