The decomposition-free logarithm is both faster and more accurate than the spectral logarithm and than the square-root approximations it replaces, and at matched basis and degree the log target beats the square-root target, confirming that the gain comes from the faithful Riemannian map rather than from a better polyno...
Md Rifat Ur Rahman, Md Raihan Khan, Md Sakib Hossain Shovon et al.· 0 citations
I-SplineFlow is introduced, which parameterizes the scheduler with integrated monotone splines (I-splines), and improves few-step FID over B\'ezier scheduling in most settings, most clearly at the lowest NFEs, and trains in minutes.
Md Sakib Hossain Shovon, Md Rifat Ur Rahman, Md Abtahi Majeed Chowdhury et al.· 0 citations
Coiflet-based wavelet convolution layers match Haar at deeper levels with approximately 32% fewer additional parameters and 33% fewer additional FLOPs, providing a concrete and actionable design choice for practitioners building wavelet-based architectures.
Global Covariance Pooling (GCP) improves deep networks by capturing second-order feature statistics, and is especially effective for fine-grained recognition. Because covariance matrices live on the Symmetric Positive Definite (SPD) manifold, a normalization step is required before the Euclidean classifier. The faithfu...
Md Rifat Ur Rahman, Md Raihan Khan, Md Sakib Hossain Shovon et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
