End-to-End Optimization of Incoherent Imaging for Classification Under Detector-Limited Readout

• URL: http://arxiv.org/abs/2606.09792v1
• Date: Mon, 08 Jun 2026 17:48:14 GMT
• Title: End-to-End Optimization of Incoherent Imaging for Classification Under Detector-Limited Readout
• Abstract summary: This paper focuses on object classification, a central imaging task, and asks when end-to-end optimization of a phase mask for incoherent imaging improves performance.<n>We find that these gains arise primarily under constrained detector readout and are limited under full detector readout.
• Score: 2.6207362827093044
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: End-to-end co-optimization of optical front-ends (e.g. metasurfaces) and neural network back-ends has been widely applied to imaging tasks, yet a formalism characterizing when and why such systems outperform conventional lens-based imaging is largely lacking. This paper focuses on object classification, a central imaging task, and asks when end-to-end optimization of a phase mask for incoherent imaging improves performance over a conventional focusing lens. We find that these gains arise primarily under constrained detector readout and are limited under full detector readout. In the latter setting, we prove that no incoherent phase mask exceeds the ideal-channel mutual information between detector measurements and class labels; a conventional focusing lens approaches this ceiling, and joint optimization yields no empirical gain. When detector readout is constrained -- by coarse spatial sampling or a limited number of measurements -- optimized optics can substantially improve classification by increasing class separability in the detector measurements. These gains are largest under low detector noise and shrink as noise grows, because the optics shape the signal before it reaches the detector but cannot remove noise added afterward. The advantage also depends on the spectral structure of the task: co-design helps most when class-discriminative content is concentrated at lower spatial frequencies than within-class variation. We develop a theoretical framework formalizing these distinctions and test its predictions on synthetic data and standard benchmarks (MNIST, FashionMNIST, SVHN).

Related papers

• Measurement-Adapted Eigentask Representations for Photon-Limited Optical Readout [7.173241044998128]
  downstream inference depends on how noisy high-dimensional sensor measurements are represented before classification or decision-making.<n>We show that eigentasks provide a measurement-adapted representation for optical sensor outputs by ordering readout features according to their resolvability under noise.
  arXiv  Detail & Related papers  (2026-05-11T05:35:08Z)
• Passive Imaging with Quantum Advantage [40.27113751459193]
  We propose and implement a method for reducing the effect of this noise by optically pre-processing the incoming light prior to detection.<n>Our scheme, termed Fourier Domain Division (FDD), partitions the Fourier plane into multiple regions for independent detection and subsequent post-processing for image reconstruction.<n>We demonstrate our method in microscopy, achieving 5-fold improvement of Fisher information on high spatial-frequency components.
  arXiv  Detail & Related papers  (2026-05-07T10:06:49Z)
• Self-Supervised Angular Deblurring in Photoacoustic Reconstruction via Noisier2Inverse [2.812291464467386]
  Photoacoustic tomography (PAT) is an emerging imaging modality that combines optical contrast and ultrasonic resolution.<n>We propose a self-supervised reconstruction method based on Noisier2Inverse that addresses finite-size detector effects without requiring ground-truth data.<n>Our approach operates directly on noisy measurements and learns to recover high-quality PAT images in a ground-truth-free manner.
  arXiv  Detail & Related papers  (2026-04-17T04:07:11Z)
• Uncertainty-Guided Selective Adaptation Enables Cross-Platform Predictive Fluorescence Microscopy [65.15943255667733]
  We introduce Subnetwork Image Translation ADDA with automatic depth selection (SIT-ADDA-Auto)<n>We show that adapting only the earliest convolutional layers, while freezing deeper layers, yields reliable transfer.<n>Our results provide a design rule for label-free adaptation in microscopy and a recipe for field settings; the code is publicly available.
  arXiv  Detail & Related papers  (2025-11-15T03:01:05Z)
• Foundation Visual Encoders Are Secretly Few-Shot Anomaly Detectors [58.75916798814376]
  We develop a few-shot anomaly detector termed FoundAD.<n>We observe that the anomaly amount in an image directly correlates with the difference in the learnt embeddings.<n>The simple operator acts as an effective tool for anomaly detection to characterize and identify out-of-distribution regions in an image.
  arXiv  Detail & Related papers  (2025-10-02T11:53:20Z)
• Crane: Context-Guided Prompt Learning and Attention Refinement for Zero-Shot Anomaly Detection [50.343419243749054]
  Anomaly detection is critical in fields such as medical diagnostics and industrial defect detection.<n> CLIP's coarse-grained image-text alignment limits localization and detection performance for fine-grained anomalies.<n>Crane improves the state-of-the-art ZSAD from 2% to 28%, at both image and pixel levels, while remaining competitive in inference speed.
  arXiv  Detail & Related papers  (2025-04-15T10:42:25Z)
• Unpaired Optical Coherence Tomography Angiography Image Super-Resolution via Frequency-Aware Inverse-Consistency GAN [6.717440708401628]
  We propose a Generative Adversarial Network (GAN)-based unpaired super-resolution method for OCTA images.<n>To facilitate a precise spectrum of the reconstructed image, we also propose a frequency-aware adversarial loss for the discriminator.<n>Experiments show that our method outperforms other state-of-the-art unpaired methods both quantitatively and visually.
  arXiv  Detail & Related papers  (2023-09-29T14:19:51Z)
• On Measuring and Controlling the Spectral Bias of the Deep Image Prior [63.88575598930554]
  The deep image prior has demonstrated the remarkable ability that untrained networks can address inverse imaging problems. It requires an oracle to determine when to stop the optimization as the performance degrades after reaching a peak. We study the deep image prior from a spectral bias perspective to address these problems.
  arXiv  Detail & Related papers  (2021-07-02T15:10:42Z)
• Light Lies: Optical Adversarial Attack [24.831391763610046]
  This paper introduces an optical adversarial attack, which physically alters the light field information arriving at the image sensor so that the classification model yields misclassification. We present experiments based on both simulation and a real hardware optical system, from which the feasibility of the proposed optical attack is demonstrated.
  arXiv  Detail & Related papers  (2021-06-18T04:20:49Z)
• Universal and Flexible Optical Aberration Correction Using Deep-Prior Based Deconvolution [51.274657266928315]
  We propose a PSF aware plug-and-play deep network, which takes the aberrant image and PSF map as input and produces the latent high quality version via incorporating lens-specific deep priors. Specifically, we pre-train a base model from a set of diverse lenses and then adapt it to a given lens by quickly refining the parameters.
  arXiv  Detail & Related papers  (2021-04-07T12:00:38Z)
• Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency Domain [88.7339322596758]
  We present a novel Spatial-Phase Shallow Learning (SPSL) method, which combines spatial image and phase spectrum to capture the up-sampling artifacts of face forgery. SPSL can achieve the state-of-the-art performance on cross-datasets evaluation as well as multi-class classification and obtain comparable results on single dataset evaluation.
  arXiv  Detail & Related papers  (2021-03-02T16:45:08Z)
• Hyperspectral-Multispectral Image Fusion with Weighted LASSO [68.04032419397677]
  We propose an approach for fusing hyperspectral and multispectral images to provide high-quality hyperspectral output. We demonstrate that the proposed sparse fusion and reconstruction provides quantitatively superior results when compared to existing methods on publicly available images.
  arXiv  Detail & Related papers  (2020-03-15T23:07:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.