Learning to Mask and Permute Visual Tokens for Vision Transformer Pre-Training.
Lorenzo BaraldiRoberto AmorosoMarcella CorniaLorenzo BaraldiAndrea PilzerRita CucchiaraPublished in: CoRR (2023)
Keyphrases
- supervised learning
- learning speed
- learning algorithm
- online training
- motor skills
- learning process
- fuzzy logic
- unsupervised learning
- real time
- visual perception
- learning tasks
- visual learning
- structured prediction
- learning machines
- reinforcement learning
- computer vision
- visual information
- online learning
- learning stage
- recurrent networks
- e learning
- deep architectures