SP-ViT: Learning 2D Spatial Priors for Vision Transformers.
Yuxuan ZhouWangmeng XiangChao LiBiao WangXihan WeiLei ZhangMargret KeuperXiansheng HuaPublished in: CoRR (2022)
Keyphrases
- prior knowledge
- learning algorithm
- learning systems
- online learning
- data sets
- real time
- supervised learning
- spatial distribution
- active learning
- learning process
- multi agent
- reinforcement learning
- image processing
- mobile robot
- vision system
- knowledge acquisition
- knowledge base
- learning tasks
- learning problems
- incremental learning
- neural network