all AI news
Do Vision and Language Encoders Represent the World Similarly?
March 26, 2024, 4:45 a.m. | Mayug Maniparambil, Raiymbek Akshulakov, Yasser Abdelaziz Dahou Djilali, Sanath Narayan, Mohamed El Amine Seddik, Karttikeya Mangalam, Noel E. O'Conno
cs.LG updates on arXiv.org arxiv.org
Abstract: Aligned text-image encoders such as CLIP have become the de facto model for vision-language tasks. Furthermore, modality-specific encoders achieve impressive performances in their respective domains. This raises a central question: does an alignment exist between uni-modal vision and language encoders since they fundamentally represent the same physical world? Analyzing the latent spaces structure of vision and language models on image-caption benchmarks using the Centered Kernel Alignment (CKA), we find that the representation spaces of unaligned …
abstract alignment arxiv become clip cs.ai cs.cl cs.cv cs.lg domains image language modal performances question raises tasks text text-image type vision world
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
Intern Large Language Models Planning (f/m/x)
@ BMW Group | Munich, DE
Data Engineer Analytics
@ Meta | Menlo Park, CA | Remote, US