SELF-ATTENTION IN FREQUENCY DOMAIN FOR IMAGE SEGMENTATION

Abstract: embodiments of the present invention provide computer-implemented methods, computer program product, and computer systems. one or more processors access an image file. the one or more processors input the image file into a deep learning model, where the deep learning model includes multiple blocks, each block of the multiple blocks including a hartley transform, mixings of features in the frequency domain with a set of learnable parameters to produce new features, and an inverse of the hartley transform. the one or more processors output another image file containing segmentation results of the accessed image file.

Inventor(s): Chun Lok Wong, HONGZHI WANG, Tanveer F. Syeda-Mahmood

CPC Classification: G06T7/11 (Region-based segmentation)

Search for rejections for patent application number 20250217990