	US 11,983,920 B2
	Unified framework for multigrid neural network architecture
Vadim Ratner, Haifa (IL); Yoel Shoshan, Haifa (IL); and Flora Gilboa-Solomon, Haifa (IL)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on Dec. 20, 2021, as Appl. No. 17/556,011.
Prior Publication US 2023/0196750 A1, Jun. 22, 2023
Int. Cl. G06V 10/82 (2022.01); G06N 3/045 (2023.01); G06V 10/764 (2022.01)

CPC G06V 10/82 (2022.01) [G06N 3/045 (2023.01); G06V 10/764 (2022.01)]

20 Claims

1. A system comprising:

at least one hardware processor; and

a non-transitory computer-readable storage medium having stored thereon program instructions, the program instructions executable by the at least one hardware processor to:

receive, as input, an image,

provide a neural network structure comprising a plurality of multilayer multi-scale neural networks, wherein the plurality of multilayer multi-scale neural networks are arranged sequentially, by laterally connecting corresponding scale-level layers between each two adjoining multilayer multi-scale neural networks in said sequence, and

at a training stage, training said neural network structure on a training dataset, to obtain a trained machine learning model configured to perform a computer vision task which comprises outputting at least one of:

(i) a classification of said image into one class of a set of two or more classes,

(ii) a segmentation of a least one object in said image, and

(iii) a detection of at least one object in said image.