i-MAE: Are Latent Representations in Masked Autoencoders Linearly Separable?

Kevin Zhang Zhiqiang Shen

Published in: CoRR (2022)

Keyphrases

linearly separable
linear separability
input space
hyperplane
linear classifiers
high dimensional feature space
feature space
infinite dimensional
convex hull
data points
decision boundary
denoising
data sets
latent variables
high dimensional data
kernel methods
sample set
neural network