Research map / Detection and segmentation / CNN features
Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detection
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| channel-wise normalization instead of layer-wise (ablation) | Spiking-YOLO · PASCAL VOC | mAP: 48.94 -> 51.83 | Helped |
| channel-wise normalization instead of layer-wise (ablation) | Spiking-YOLO · MS COCO | mAP: 24.66 -> 25.66 | Helped |
| add signed neuron with imbalanced threshold (ablation) | Spiking-YOLO · PASCAL VOC | mAP: 5.61 -> 51.83 | Helped |
| Vmem-based output decoding instead of spike count (ablation) | Spiking-YOLO · PASCAL VOC | mAP: 47.19 -> 51.83 | Helped |
| channel-norm instead of layer-norm (ablation) | Spiking-YOLO · PASCAL VOC | time steps to converge: 2.3x faster | Helped |
| convert Tiny YOLO to SNN on TrueNorth | Tiny YOLO · energy per image | energy: ~280x less energy | Helped |
Closest papers by meaning
- SpikingYOLOX: Improved YOLOX Object Detection with Fast Fourier Convolution and Spiking Neural Networks (AAAI 2025 · similarity 0.94)
- 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)
- CREST: An Efficient Conjointly-trained Spike-driven Framework for Event-based Object Detection Exploiting Spatiotemporal Dynamics (AAAI 2025 · similarity 0.89)
- Efficient Event-Based Object Detection: A Hybrid Neural Network with Spatial and Temporal Attention (CVPR 2025 · similarity 0.89)
- Inference-Scale Complexity in ANN-SNN Conversion for High-Performance and Low-Power Applications (CVPR 2025 · similarity 0.88)
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.