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

6 May 2021

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

8 / 8 papers shown

Title
KrADagrad: Kronecker Approximation-Domination Gradient Preconditioned Stochastic Optimization Jonathan Mei Alexander Moreno Luke Walters ODL 24 1 0 30 May 2023
Learning Partial Correlation based Deep Visual Representation for Image Classification Saimunur Rahman Piotr Koniusz Lei Wang Luping Zhou Peyman Moghadam Changming Sun SSL 27 9 0 23 Apr 2023
Orthogonal SVD Covariance Conditioning and Latent Disentanglement Yue Song N. Sebe Wei Wang 26 6 0 11 Dec 2022
Grouping-matrix based Graph Pooling with Adaptive Number of Clusters Sung Moon Ko Sungjun Cho Dae-Woong Jeong Sehui Han Moontae Lee Ho Hin Lee 16 9 0 07 Sep 2022
Batch-efficient EigenDecomposition for Small and Medium Matrices Yue Song N. Sebe Wei Wang 29 2 0 09 Jul 2022
Improving Covariance Conditioning of the SVD Meta-layer by Orthogonality Yue Song N. Sebe Wei Wang 16 8 0 05 Jul 2022
On the Eigenvalues of Global Covariance Pooling for Fine-grained Visual Recognition Yue Song N. Sebe Wei Wang 23 33 0 26 May 2022
Fast Differentiable Matrix Square Root and Inverse Square Root Yue Song N. Sebe Wei Wang 27 15 0 29 Jan 2022