Masking principal components instead of pixel patches in masked autoencoders yields better image classification representations across CIFAR10, TinyImageNet, and three MedMNIST datasets.
Example images from the (from left to right) DermaMNIST, PathMNIST, and BloodMNIST datasets used for image classification
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
From Pixels to Components: Eigenvector Masking for Visual Representation Learning
Masking principal components instead of pixel patches in masked autoencoders yields better image classification representations across CIFAR10, TinyImageNet, and three MedMNIST datasets.