CAST: Clustering Self-Attention using Surrogate Tokens for Efficient Transformers.

Adjorn van Engelenhoven Nicola Strisciuglio Estefanía Talavera

Published in: CoRR (2024)

Keyphrases

clustering method
k means
lightweight
information theoretic
artificial intelligence
computer vision
neural network
clustering algorithm
decision trees
similarity measure
data structure
pairwise
cluster analysis