Single Snapshot Distillation for Phase Coded Mask Design in Phase Retrieval

TL;DR

This paper proposes a knowledge distillation method to enable phase retrieval systems to reconstruct images from a single snapshot, improving efficiency and performance over multi-snapshot trained systems.

Contribution

It introduces a novel single snapshot distillation approach that transfers knowledge from a multi-snapshot trained teacher to a single snapshot student in phase retrieval.

Findings

Single snapshot distillation improves reconstruction quality.

The method outperforms systems trained without teacher guidance.

Efficient single snapshot phase retrieval is achieved.

Abstract

Phase retrieval (PR) reconstructs phase information from magnitude measurements, known as coded diffraction patterns (CDPs), whose quality depends on the number of snapshots captured using coded phase masks. High-quality phase estimation requires multiple snapshots, which is not desired for efficient PR systems. End-to-end frameworks enable joint optimization of the optical system and the recovery neural network. However, their application is constrained by physical implementation limitations. Additionally, the framework is prone to gradient vanishing issues related to its global optimization process. This paper introduces a Knowledge Distillation (KD) optimization approach to address these limitations. KD transfers knowledge from a larger, lower-constrained network (teacher) to a smaller, more efficient, and implementable network (student). In this method, the teacher, a PR system trained with multiple snapshots, distills its knowledge into a single-snapshot PR system, the student. The loss functions compare the CPMs and the feature space of the recovery network. Simulations demonstrate that this approach improves reconstruction performance compared to a PR system trained without the teacher's guidance.