Diffractive optical networks with scale, shift, and rotation invariance

Deniz Mengu; Yair Rivenson; Aydogan Ozcan

doi:10.1117/12.2609500

9 March 2022 Diffractive optical networks with scale, shift, and rotation invariance

Deniz Mengu, Yair Rivenson, Aydogan Ozcan

Proceedings Volume PC12019, AI and Optical Data Sciences III; PC120190M (2022) https://doi.org/10.1117/12.2609500
Event: SPIE OPTO, 2022, San Francisco, California, United States

Abstract

This study reports a new diffractive optical network design strategy that incorporates object scaling, translation, and rotation as part of the forward training model using uniformly-distributed random variables to provide immunity and resilience against such variations at the input object plane. By guiding the evolution of the diffractive layers towards a scale-, shift- and rotation-invariant network solution, this training strategy provides >30-70% improvement in the all-optical blind inference accuracies achieved under various unknown object transformations. This training method constitutes a promising approach to bring the advantages of all-optical diffractive inference with low-latency, power-efficiency, and parallelization to various machine vision applications.

Conference Presentation

Citation Download Citation

Deniz Mengu, Yair Rivenson, and Aydogan Ozcan "Diffractive optical networks with scale, shift, and rotation invariance", Proc. SPIE PC12019, AI and Optical Data Sciences III, PC120190M (9 March 2022); https://doi.org/10.1117/12.2609500

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available