A Retinomorphic Optical Spiking Neuron for Camouflaged Object Detection

• URL: http://arxiv.org/abs/2606.00818v1
• Date: Sat, 30 May 2026 17:36:02 GMT
• Title: A Retinomorphic Optical Spiking Neuron for Camouflaged Object Detection
• Abstract summary: Advanced vision systems require retinomorphic, energy-efficient spike-based preprocessing of dynamic visual scenes.<n>We demonstrate retinal preprocessing functionalities by leveraging a Hodgkin-Huxley-based optical spiking neuron (OSHN)<n>OSHN exhibits wavelength- and intensity-sensitive spike encoding with energy consumption per spike of 0.9 pJ under dark, 2 pJ at 480 nm (mid wavelength, M), and 24.5 pJ at 800 nm (long wavelength, L)
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Advanced vision systems require retinomorphic, energy-efficient spike-based preprocessing of dynamic visual scenes. Here, we demonstrate multiple retinal preprocessing functionalities by leveraging a Hodgkin-Huxley-based optical spiking neuron (OSHN) that incorporates a two-dimensional anti-ambipolar phototransistor operated in the subthreshold regime to minimize power consumption. OSHN exhibits wavelength- and intensity-sensitive spike encoding with energy consumption per spike of 0.9 pJ under dark, 2 pJ at 480 nm (mid wavelength, M), and 24.5 pJ at 800 nm (long wavelength, L). The low (biological)-to-high spiking rate (0 - 2 kHz) with substantially faster response times (4.2 $μ$s - 1.25 ms) than the human retina (30 ms - 60 ms), reveal OSHN's fast decision-making capability. OSHN facilitates concurrent spectral-spatial processing by emulating retinal antagonistic center-surround receptive fields (CSRFs) at a single wavelength (480 nm or 800 nm) with varying intensities, visual adaptation (at 480 nm) to prevent system saturation, and L-M cone opponency in midget ganglion cells. Finally, a CSRF-augmented spiking neural network (SNN) has been developed for camouflaged object detection, achieving 4.4%, 10.4%, and 28.4% improvements in accuracy over conventional SNN on FMNIST, COD10K, and synthetic camouflaged datasets, outperforming existing photoactive spiking architectures while enabling event-driven intelligent edge vision systems.

Related papers

• Beyond the Thin-Layer Limit: Differentiable Volumetric Training for Visible-Range Diffractive Neural Networks [0.0]
  Translating D2NNs to the visible range, where nearly all vision pipelines operate, was long blamed on the difficulty of fabricating nanoscale neurons.<n>We identify the true obstacle as the thin-layer approximation underlying nearly all D2NN training, which treats each diffractive layer as an infinitely thin mask.<n>We introduce a differentiable beam-propagation layer that models each element as a finite-thickness volume and propagates light through it during training, keeping the fabrication-compatible height map end-to-end trainable.
  arXiv  Detail & Related papers  (2026-06-05T23:14:06Z)
• PHASE-Net: Physics-Grounded Harmonic Attention System for Efficient Remote Photoplethysmography Measurement [63.007237197267834]
  Existing deep learning methods are mostly physiological monitoring and lack theoretical robustness.<n>We propose a physics-informed r paradigm derived from the Navier-Stokes equations of hemodynamics, showing that the pulse signal follows a second-order system.<n>This provides a theoretical justification for using a Temporal Conal Network (TCN)<n>Phase-Net achieves state-of-the-art performance with strong efficiency, offering a theoretically grounded and deployment-ready r solution.
  arXiv  Detail & Related papers  (2025-09-29T14:36:45Z)
• Neuromorphic Wireless Split Computing with Resonate-and-Fire Neurons [69.73249913506042]
  This paper investigates a wireless split computing architecture that employs resonate-and-fire (RF) neurons to process time-domain signals directly.<n>By resonating at tunable frequencies, RF neurons extract time-localized spectral features while maintaining low spiking activity.<n> Experimental results show that the proposed RF-SNN architecture achieves comparable accuracy to conventional LIF-SNNs and ANNs.
  arXiv  Detail & Related papers  (2025-06-24T21:14:59Z)
• Reliable Noninvasive Glucose Sensing via CNN-Based Spectroscopy [0.36868085124383626]
  We present a dual-modal AI framework based on short-wave infrared (SWIR) spectroscopy.<n>The first modality employs a multi-wavelength SWIR imaging system coupled with convolutional neural networks (CNNs) to capture spatial features linked to glucose absorption.<n>The second modality uses a compact photodiode voltage sensor and machine learning regressors (e.g., random forest) on normalized optical signals.
  arXiv  Detail & Related papers  (2025-06-15T03:01:15Z)
• SpikeSMOKE: Spiking Neural Networks for Monocular 3D Object Detection with Cross-Scale Gated Coding [40.87826765639894]
  SpikeSMOKE is a new attempt for low-power monocular 3D object detection.<n>SpikeSMOKE can significantly reduce energy consumption compared to the results on SMOKE.
  arXiv  Detail & Related papers  (2025-06-09T13:20:10Z)
• Frequency Domain Enhanced U-Net for Low-Frequency Information-Rich Image Segmentation in Surgical and Deep-Sea Exploration Robots [34.28684917337352]
  We address the differences in frequency band sensitivity between CNNs and the human visual system.<n>We propose a wavelet adaptive spectrum fusion (WASF) method inspired by biological vision mechanisms to balance cross-frequency image features.<n>We develop the FE-UNet model, which employs a SAM2 backbone network and incorporates fine-tuned Hiera-Large modules to ensure segmentation accuracy.
  arXiv  Detail & Related papers  (2025-02-06T07:24:34Z)
• A spiking photonic neural network of 40.000 neurons, trained with rank-order coding for leveraging sparsity [0.2386578882591578]
  Spiking neural networks are neuromorphic systems that emulate certain aspects of biological neurons.<n>This demonstration integrates photonic nonlinearity, excitability, and sparse computation, paving the way for efficient large-scale photonic neuromorphic systems.
  arXiv  Detail & Related papers  (2024-11-28T15:28:30Z)
• Bandwidth-tunable Telecom Single Photons Enabled by Low-noise Optomechanical Transduction [45.37752717923078]
  Single-photon sources are of fundamental importance to emergent quantum technologies. Nano-structured optomechanical crystals provide an attractive platform for single photon generation. Optical absorption heating has thus far prevented these systems from being widely used in practical applications.
  arXiv  Detail & Related papers  (2024-10-14T18:00:00Z)
• Fabrication of Sawfish photonic crystal cavities in bulk diamond [0.0]
  "Sawfish" cavities are proposed to enhance the emission rate by a factor of 46 and couple photons into a single-mode fiber with an efficiency of 88%. The presented process allows for the fabrication of fully suspended devices with a total length of 20.5 $mu$m and features size as small as 40 nm.
  arXiv  Detail & Related papers  (2023-11-07T00:05:46Z)
• Classification robustness to common optical aberrations [64.08840063305313]
  This paper proposes OpticsBench, a benchmark for investigating robustness to realistic, practically relevant optical blur effects. Experiments on ImageNet show that for a variety of different pre-trained DNNs, the performance varies strongly compared to disk-shaped kernels. We show on ImageNet-100 with OpticsAugment that can be increased by using optical kernels as data augmentation.
  arXiv  Detail & Related papers  (2023-08-29T08:36:00Z)
• The Expressive Leaky Memory Neuron: an Efficient and Expressive Phenomenological Neuron Model Can Solve Long-Horizon Tasks [64.08042492426992]
  We introduce the Expressive Memory (ELM) neuron model, a biologically inspired model of a cortical neuron. Our ELM neuron can accurately match the aforementioned input-output relationship with under ten thousand trainable parameters. We evaluate it on various tasks with demanding temporal structures, including the Long Range Arena (LRA) datasets.
  arXiv  Detail & Related papers  (2023-06-14T13:34:13Z)
• Online optimization for optical readout of a single electron spin in diamond [16.847282439998885]
  We introduce an online optimization method to customize the laser waveform for readout. The SNR of optical spin readout has been witnessed a 44.1% increase in experiments. This scheme is promising to improve sensitivities for a wide range of NV-based applications in the future.
  arXiv  Detail & Related papers  (2022-12-19T02:06:53Z)
• Laser threshold magnetometry using green light absorption by diamond nitrogen vacancies in an external cavity laser [52.77024349608834]
  Nitrogen vacancy (NV) centers in diamond have attracted considerable recent interest for use in quantum sensing. We show theoretical sensitivity to magnetic field on the pT/sqrt(Hz) level is possible using a diamond with an optimal density of NV centers.
  arXiv  Detail & Related papers  (2021-01-22T18:58:05Z)

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.