ManagerTower: Aggregating the Insights of Uni-Modal Experts for Vision-Language Representation Learning.
Xiao XuBei LiChenfei WuShao-Yen TsengAnahita BhiwandiwallaShachar RosenmanVasudev LalWanxiang CheNan DuanPublished in: CoRR (2023)
Keyphrases
- learning systems
- real time
- learning process
- online learning
- learning algorithm
- multiple representations
- prior knowledge
- highly expressive
- conceptual graphs
- learning problems
- knowledge acquisition
- vision system
- supervised learning
- active learning
- reinforcement learning
- neural network
- programming language
- image representation
- human experts
- language learning
- object oriented programming
- language acquisition
- image processing