Research map / Detection and segmentation / CNN features
Bio-Vision-Inspired Spiking Neural Networks for Object Detection with Event Cameras
Dongyang Ma, Zhengyu Ma, Yifan Huang, Chenlin Zhou, Wei Zhang, Yonghong Tian
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add STATNFN neuron in place of SPSN5 (ablation) | STATNF-BiSNet · N-Caltech101 | mAP50:90 (%): 40.0 -> 45.0 | Improved |
| add STATNFN neuron in place of SPSN5 (ablation) | STATNF-BiSNet · N-Caltech101 | firing rate (%): 28.0 -> 14.1 | Improved |
| add STATNFN neuron in place of SPSN5 (ablation) | MS-ResNet · N-Caltech101 | mAP50:90 (%): 37.8 -> 38.0 | No clear effect |
| add STATNFN neuron in place of SPSN5 (ablation) | MS-ResNet · N-Caltech101 | firing rate (%): 19.3 -> 14.9 | Improved |
| add STATNFN neuron in place of SPSN5 (ablation) | EMS-ResNet · N-Caltech101 | firing rate (%): 30.0 -> 16.0 | Improved |
| add STATNFN neuron in place of SPSN5 (ablation) | EMS-ResNet · N-Caltech101 | mAP50:90 (%): 37.0 -> 37.9 | Improved |
| add STATNF, E2S and BiS to the base network (ablation) | base SNN · N-Caltech101 | mAP50:90: 0.373 -> 0.450 | Improved |
| add STATNF, E2S and BiS to the base network (ablation) | base SNN · N-Caltech101 | firing rate: 0.371 -> 0.141 | Improved |
| use STATNFN across 30 architecture-neuron combinations (ablation) | SNNs · N-CARS | firing rate | Improved |
| use E2S+STATNF-BiSNet instead of CREST | CREST · Gen1 | mAP50:90: 0.360 -> 0.400 | Improved |
| use E2S+STATNF-BiSNet instead of CREST | CREST · Gen1 | energy (mJ): 6.31 -> 1.48 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- EAS-SNN — EAS-SNN: End-to-End Adaptive Sampling and Representation for Event-based Detection with Recurrent Spiking Neural Networks (ECCV 2024) · better on 3 of 3 shared results
- SFOD — SFOD: Spiking Fusion Object Detector (CVPR 2024) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Brain-Inspired Spiking Neural Networks for Energy-Efficient Object Detection (CVPR 2025 · similarity 0.92)
- SFOD: Spiking Fusion Object Detector (CVPR 2024 · similarity 0.90)
- Efficient Event-Based Object Detection: A Hybrid Neural Network with Spatial and Temporal Attention (CVPR 2025 · similarity 0.89)
- Leveraging Asynchronous Spiking Neural Networks for Ultra Efficient Event-Based Visual Processing (AAAI 2025 · similarity 0.88)
- SpikingYOLOX: Improved YOLOX Object Detection with Fast Fourier Convolution and Spiking Neural Networks (AAAI 2025 · similarity 0.88)
- CREST: An Efficient Conjointly-trained Spike-driven Framework for Event-based Object Detection Exploiting Spatiotemporal Dynamics (AAAI 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
