LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference.
Benjamin GrahamAlaaeldin El-NoubyHugo TouvronPierre StockArmand JoulinHervé JégouMatthijs DouzePublished in: CoRR (2021)
Keyphrases
- computer vision
- vision system
- real time
- inference process
- fuzzy logic
- inference mechanism
- human body
- probabilistic inference
- information retrieval
- inference engine
- high voltage
- bayesian model
- human vision
- visual perception
- dynamic bayesian networks
- bayesian inference
- fault diagnosis
- power system
- maximum likelihood
- bayesian networks
- image processing
- social networks