Published January 2, 2025
| Version v1
Dataset
Open
CIFAR10 statistics and PCA
Description
CIFAR10 mean (mean_reshaped.npy) and standard deviation (std_reshaped.npy) calculated on the training set;
CIFAR10's covariance matrix's eigenvalues (eigenvalues.npy), the ratio of total variance explained by each principal component (eigenvalues_ratio.npy), eand CIFAR10's principal components (pc_matrix.npy) computed using the normalized training dataset.
These items were used in [1].
[1] Alice Bizeul, Thomas M. Sutter, Alain Ryser, Julius Von Kügelgen, Bernhard Schölkopf, Julia E. Vogt. Components Beat Patches: Eigenvector Masking for Visual Representation Learning. Oct, 2024.
Files
Files
(37.8 MB)
Additional details
Identifiers
Dates
- Submitted
-
2025-01-02
Software
- Repository URL
- https://github.com/alicebizeul/pmae
- Programming language
- Python
- Development Status
- Active
References
- Alice Bizeul, Thomas M. Sutter, Alain Ryser, Julius Von Kügelgen, Bernhard Schölkopf, Julia E. Vogt. Components Beat Patches: Eigenvector Masking for Visual Representation Learning. Oct, 2024.