Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
Spiking neural networks (SNNs) for event-based optical flow are claimed to be computationally more efficient than their artificial neural networks (ANNs) counterparts, but a fair comparison is missing in the literature. In this work, we propose an event-based optical flow solution based on activation sparsification and a neuromorphic processor, SENECA. SENECA has an event-driven processing mechanism that can exploit the sparsity in ANN activations and SNN spikes to accelerate the inference of both types of neural networks. The ANN and the SNN for comparison have similar low activation/spike density (∼5%) thanks to our novel sparsification-aware training. In the hardware-in-loop experiments designed to deduce the average time and energy consumption, the SNN consumes 44.9ms and 927.0μJ, which are 62.5% and 75.2% of the ANN's consumption, respectively. We find that SNN's higher efficiency is attributed to its lower pixel-wise spike density (43.5% vs. 66.5%) that requires fewer memory access operations for neuron states.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.neunet.2025.107447 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
[Progression assessment of glaucoma].
Ophthalmologie
September 2025
Augenzentrum am St. Franziskus-Hospital Münster, Hohenzollernring 74, 48145, Münster, Deutschland.
Progression monitoring is essential for glaucoma management. In addition to perimetry, optical coherence tomography (OCT) has become established as a valuable supplement. It provides morphological information on the retinal nerve fiber layer (RNFL), the neuroretinal rim and the density of retinal ganglion cells in the macula.
View Article and Find Full Text PDFComparing the utility of retinal nerve fiber layer and ganglion cell inner plexiform layer OCT changes to detect glaucoma progression.
Ophthalmology
August 2025
Wilmer Eye Institute, Johns Hopkins University School of Medicine, Baltimore, MD, USA; Malone Center for Engineering in Healthcare, Johns Hopkins University, Baltimore, Maryland. Electronic address:
Objective: Measure and compare the rates of circumpapillary retinal nerve fiber layer (cpRNFL) and macular ganglion cell-inner plexiform layer (mGCIPL) thinning in glaucomatous eyes with and without visual field (VF) progression, across a broad range of disease severity, in a large clinical population.
Design: Retrospective, longitudinal study SUBJECTS: 2,464 eyes (1,605 patients) with longitudinal testing (≥ 5 reliable cpRNFL, mGCIPL, and VF measurements). All cpRNFL and mGCIPL measurements were within 1 year of a VF test.
Anticipatory eye gaze as a marker of memory.
Commun Psychol
August 2025
Sagol School of Neuroscience, Tel Aviv University, Tel Aviv, Israel.
Human memory is typically studied by direct questioning, and the recollection of events is investigated through verbal reports. Thus, current research confounds memory per-se with its report. Critically, the ability to investigate memory retrieval in populations with deficient verbal ability is limited.
View Article and Find Full Text PDFEvent-Based Visual Microphone Based On Specular Reflections Off Angularly Deformed Surfaces.
IEEE Trans Pattern Anal Mach Intell
August 2025
We propose and demonstrate the event-based visual microphone (EBVM), a passive electro-optical technique for remotely capturing audio signals using an event-based camera without any use of a conventional microphone. The event-based camera records local angular deformations of a surface induced by the sound propagation by observing the changes in the specular reflections at each pixel. By interpreting the timings of the specular incidences deduced from the event stream as signal level-crossings, we reconstruct the audio signal by imposing short-time Fourier sparsity conditions.
View Article and Find Full Text PDFST-FlowNet: An efficient Spiking Neural Network for event-based optical flow estimation.
Neural Netw
October 2025
Clinical Hospital of Chengdu Brain Science Institute, MOE Key Lab for NeuroInformation, China-Cuba Belt and Road Joint Laboratory on Neurotechnology and Brain-Apparatus Communication, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu 611731, Chi
Spiking Neural Networks (SNNs) have emerged as a promising tool for event-based optical flow estimation tasks due to their capability for spatio-temporal information processing and low-power computation. However, the performance of SNN models is often constrained, limiting their applications in real-world scenarios. To address this challenge, we propose ST-FlowNet, a novel neural network architecture specifically designed for optical flow estimation from event-based data.
View Article and Find Full Text PDF