Why Approximate Matrix Square Root Outperforms Accurate SVD in Global Covariance Pooling?

Yue Song Nicu Sebe Wei Wang

Published in: ICCV (2021)

Keyphrases

square root
singular value decomposition
floating point
kalman filtering
arrival rate
covariance matrix
least squares
computationally efficient
singular values
probability density function
probabilistic model
dimensionality reduction
euclidean space