Md Raihan Khan

Md Raihan Khan

Lecturer in EEE (North Western University) & B.Sc. graduate (KUET). Efficient, geometry-aware deep learning: generative modeling, optimal transport, and neural signals.

Trigonometric B-Spline Convolutional KAN for Texture Classification

Published in Eighteenth Asian Conference on Computer Vision (ACCV) — under review, 2026, 2026

This work develops a Kolmogorov–Arnold Network (KAN) built on trigonometric B-spline convolutional bases for texture classification, exploring learnable spline activations as an alternative to fixed nonlinearities in convolutional models.

Recommended citation: Md Rifat Ur Rahman, Md Raihan Khan, Resadul Islam, and Mahfuja Akter, "Trigonometric B-Spline Convolutional KAN for Texture Classification," ACCV 2026 (under review).