VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts.
Hangbo BaoWenhui WangLi DongQiang LiuOwais Khan MohammedKriti AggarwalSubhojit SomSonghao PiaoFuru WeiPublished in: NeurIPS (2022)
Keyphrases
- multi modal
- natural language
- programming language
- language learning
- online learning
- training set
- real time
- mixture model
- vision system
- medical images
- visual perception
- computer vision
- training examples
- training algorithm
- language processing
- target language
- unified model
- training phase
- subject matter experts
- training process
- domain experts
- active learning
- expert systems
- e learning
- artificial intelligence
- neural network