Sequence-SOD: Bio-inspired Sequence-aware Spiking Object Detection for Event Cameras

2026/07/29 by Katharina Bendig, René Schuster, Didier Stricker
Computer Science · Engineering · #Advanced Memory and Neural Computing #Ferroelectric and Negative Capacitance Devices #Neural Networks and Reservoir Computing #cs.CV

paper · pdf · doi:10.1007/s12559-026-10637-z

published as Cognitive Computation, vol. 18, Article 91 (2026)

arxiv created 2026/07/29 · openalex publication_date 2026/07/29 · arxiv updated 2026/07/30 · openalex created_date 2026/07/30 · openalex updated_date 2026/07/31

Abstract

Abstract Event cameras follow a retina-inspired sensing principle, reporting local intensity changes asynchronously with high temporal resolution and a wide dynamic range. Spiking Neural Networks (SNNs) complement these sparse event streams through brain-inspired dynamics, using sparse spikes and leaky membrane potentials to integrate information over time. However, many SNN object detectors process isolated event intervals with a single label and reset the network state after each prediction, thereby underusing temporal information in continuous event streams. We introduce Sequence-SOD, a sequence-aware SNN object detector that processes extended event sequences containing labels at multiple time points. Events are accumulated into short intervals, discretized into temporal steps, and fed sequentially to an SSD-style Spiking DenseNet while preserving membrane potentials across intervals within a sequence, so that detection is driven by an evolving neural state instead of independently reset input windows. On the Gen1 Automotive Detection Dataset, sequence-aware training improves mAP from 23.38 for single-interval training to 25.30 without augmentation and to 26.88 with event-data augmentation. The model achieves a theoretical prediction frequency of 40 Hz. Training and evaluating SNN object detectors on extended event sequences improves their ability to exploit temporal cues while preserving the energy-efficiency benefits of sparse spiking computation. The results highlight sequence-aware training as a complementary direction to architectural improvements for event-based SNN detection.

Citations

• Hybrid Spiking Vision Transformer for Object Detection with Event Cameras
• EvRT-DETR: Latent Space Adaptation of Image Detectors for Event-based Vision
• Integer-Valued Training and Spike-Driven Inference Spiking Neural Network for High-performance and Energy-efficient Object Detection
• SFOD: Spiking Fusion Object Detector
• Spiking CenterNet: A Distillation-boosted Spiking Neural Network for Object Detection
• Trainable Spiking-YOLO for low-latency and high-performance object detection
• GET: Group Event Transformer for Event-Based Vision
• Deep Directly-Trained Spiking Neural Networks for Object Detection
• DETRs Beat YOLOs on Real-time Object Detection
• Recurrent Vision Transformers for Object Detection with Event Cameras
• Object Detection with Spiking Neural Networks on Automotive Event Data
• Beyond Classification: Directly Training Spiking Neural Networks for Semantic Segmentation
• YOLOX: Exceeding YOLO Series in 2021
• Learning to Detect Objects with a 1 Megapixel Event Camera
• A Large Scale Event-based Detection Dataset for Automotive
• Rethinking the performance comparison between SNNS and ANNS
• Surrogate Gradient Learning in Spiking Neural Networks
• Surrogate Gradient Learning in Spiking Neural Networks: Bringing the Power of Gradient-Based Optimization to Spiking Neural Networks
• Direct Training for Spiking Neural Networks: Faster, Larger, Better
• Asynchronous Convolutional Networks for Object Detection in Neuromorphic Cameras
• YOLOv3: An Incremental Improvement
• Quantization and Training of Neural Networks for Efficient\n Integer-Arithmetic-Only Inference
• Densely Connected Convolutional Networks
• Efficient Event-Based Object Detection: A Hybrid Neural Network with Spatial and Temporal Attention
• Networks of spiking neurons: The third generation of neural network models
• A 128×128 120 dB 15 μs Latency Asynchronous Temporal Contrast Vision Sensor
• Event-Based Vision: A Survey
• DETRs Beat YOLOs on Real-time Object Detection

Related

• Object Detection with Spiking Neural Networks on Automotive Event Data
• EAS-SNN: End-to-End Adaptive Sampling and Representation for Event-based Detection with Recurrent Spiking Neural Networks
• Learning from Dense Events: Towards Fast Spiking Neural Networks Training via Event Dataset Distillation
• SFOD: Spiking Fusion Object Detector
• CREST: An Efficient Conjointly-trained Spike-driven Framework for Event-based Object Detection Exploiting Spatiotemporal Dynamics