all AI news
Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Representation Learning
April 12, 2024, 4:42 a.m. | Simon Schrodi, David T. Hoffmann, Max Argus, Volker Fischer, Thomas Brox
cs.LG updates on arXiv.org arxiv.org
Abstract: Contrastive vision-language models like CLIP have gained popularity for their versatile applicable learned representations in various downstream tasks. Despite their successes in some tasks, like zero-shot image recognition, they also perform surprisingly poor on other tasks, like attribute detection. Previous work has attributed these challenges to the modality gap, a separation of image and text in the shared representation space, and a bias towards objects over other factors, such as attributes. In this work we …
abstract arxiv bias clip cs.cv cs.lg effects gap image image recognition information language language models object recognition representation representation learning tasks type vision vision-language models zero-shot
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
Risk Management - Machine Learning and Model Delivery Services, Product Associate - Senior Associate-
@ JPMorgan Chase & Co. | Wilmington, DE, United States
Senior ML Engineer (Speech/ASR)
@ ObserveAI | Bengaluru