Exploration of the generalization and hallucination in deep learning: a study based on imaging through scattering medium

Honglin Liu; Xuyu Zhang; Gengchen Xie

doi:10.1117/12.3056875

10 January 2025 Exploration of the generalization and hallucination in deep learning: a study based on imaging through scattering medium

Honglin Liu, Xuyu Zhang, Gengchen Xie

Author Affiliations +

Proceedings Volume 13507, Seventeenth International Conference on Photonics and Imaging in Biology and Medicine (PIBM 2024); 1350704 (2025) https://doi.org/10.1117/12.3056875
Event: Seventeenth International Conference on Photonics and Imaging in Biology and Medicine (PIBM 2024), 2024, Shaya, China

Abstract

With fast developments of computational power and algorithms, deep learning has made breakthroughs and been applied in many fields. However, generalization remains to be a major challenge, and the limited generalization capability severely constrains applications of deep learning in practice. The hallucinations issue is another unresolved conundrum faced by deep learning and large models. By leveraging a physical model of imaging through scattering media, we studied the lack of generalization to datasets and system response functions in deep learning respectively, identified their causes, and proposed universal solutions. The research also provides an explanation for hallucinations. In general, it enhances the interpretability of deep learning from a physics-based perspective. It will pave a way for direct interaction between deep learning and the physical world, facilitating the transition of deep learning from a demo model to a practical tool.

(2025) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Honglin Liu, Xuyu Zhang, and Gengchen Xie "Exploration of the generalization and hallucination in deep learning: a study based on imaging through scattering medium", Proc. SPIE 13507, Seventeenth International Conference on Photonics and Imaging in Biology and Medicine (PIBM 2024), 1350704 (10 January 2025); https://doi.org/10.1117/12.3056875

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