Measurement-Adapted Eigentask Representations for Photon-Limited Optical Readout

2026-05-11

AI Summary

This work addresses the challenge of high-dimensional sensing under extremely low-light conditions, where optical readout is fundamentally limited by photon shot noise, detector noise, and quantization error, severely degrading performance in downstream classification tasks. The study introduces the eigentask framework into photon-starved scenarios for the first time, proposing a measurement-adaptive representation method grounded in feature discriminability. By constructing low-dimensional representations aligned with the underlying noise characteristics, the approach preferentially preserves information that remains discriminative despite noise corruption. Experiments demonstrate that the proposed method substantially outperforms baseline techniques such as principal component analysis and filtered compressive sensing on challenging few-shot classification benchmarks like MPEG-7. Notably, its performance advantage widens to approximately 10 percentage points as the number of classes increases, effectively enhancing both feature informativeness and sample efficiency.

Abstract

Optical readout in low-light imaging is fundamentally limited by measurement noise, including photon shot noise, detector noise, and quantization error. In this regime, downstream inference depends not only on the optical front end, but also on how noisy high-dimensional sensor measurements are represented before classification or decision-making. Here we show that eigentasks provide a measurement-adapted representation for optical sensor outputs by ordering readout features according to their resolvability under noise. Using experimental data from a lens-based optical imaging system and a reanalysis of published data from a single-photon-detection neural network, we find that eigentask representations frequently outperform standard baselines including principal component analysis and filtering-based compression. The advantage is most pronounced in photon-limited, few-shot, and higher-difficulty classification regimes. In few-shot MPEG-7 classification, for example, the advantage over other methods reaches about 10 percentage points as the number of classes increases. In these settings, eigentasks yield more informative low-dimensional features and improve sample-efficient downstream learning. These results identify measurement-adapted representation as a promising strategy for optical inference when photon budget, acquisition time, and task complexity are constrained.

Problem

• photon-limited imaging
• measurement noise
• optical readout
• sensor representation
• low-light imaging

Innovation

• eigentasks
• measurement-adapted representation
• photon-limited imaging
• few-shot classification
• optical readout