Single-Layer Vision Transformers for More Accurate Early Exits with Less Overhead.

Arian Bakhtiarnia Qi Zhang Alexandros Iosifidis

Published in: CoRR (2021)

Keyphrases

single layer
neural network
multi layer
neural nets
multiple layers
activation function
computer vision
feed forward neural networks
video sequences
high quality
hidden layer
genetic algorithm
multiresolution
wavelet transform
feed forward
multiscale
scalable video coding
hopfield neural network