Yonis Gulzar

High-Rank Grouped Delta Operators Enable Dynamic Geometric Transformations in Residual Networks

HRG-Delta replaces standard residual rank-1 reflections with rank-$r$ grouped subspace transformations, using dynamically generated orthonormal bases and bounded gating coefficients.

High-Rank Grouped Delta Operators Enable Dynamic Geometric Transformations in Residual Networks

HRG-Delta replaces standard residual rank-1 reflections with rank-$r$ grouped subspace transformations, using dynamically generated orthonormal bases and bounded gating coefficients.

Comparative analysis of automatic mask generation methods for agricultural seed instance segmentation

In agricultural image analysis, training deep learning models relies on large amounts of pixel-level labeled data. However, individually labeling densely stacked and overlapping objects, such as pea seeds, is both time-consuming and laborious. This study compares five automated m...