MAST: Masked Augmentation Subspace Training for Generalizable Self-Supervised Priors.

Chen Huang Hanlin Goh Jiatao Gu Joshua M. Susskind

Published in: ICLR (2023)

Keyphrases

training set
training process
low dimensional
training algorithm
high dimensional data
feature space
computer vision
bayesian framework
principal component analysis
data points
training examples
pattern recognition
face recognition
decision trees
neural network
lower dimensional
learned from training data