Research map / Architectures and efficiency / Spiking networks
Temporal Dynamics Enhancer for Directly Trained Spiking Object Detectors
Fan Luo, Zeyu Gao, Xinhao Luo, Kai Zhao, Yanfeng Lu
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 Spiking Encoder (SE) alone to SpikeYOLO (ablation) | SpikeYOLO · VOC2007 | mAP@50-95: 31.9 -> 34.6 | Improved |
| add AGM attention gating to couple SE with attention (SDA) (ablation) | SpikeYOLO · VOC2007 | mAP@50-95: 34.6 -> 35.6 | Improved |
| add attention gating (Alg. 1) on top of TCSA + SE (ablation) | SpikeYOLO · VOC (VOC2007+VOC2012) | mAP@50-95: 57.0 -> 57.7 | Improved |
| add multi-dimensional attention (TCSA) alone, no SE (ablation) | SpikeYOLO · VOC2007 | mAP@50-95: 31.9 -> 33.9 | Improved |
| add SE alone to EMSYOLO (ablation) | EMSYOLO · VOC2007 | mAP@50-95: 33.2 -> 34.1 | Improved |
| add full TDE (TCSA) to SpikeYOLO | SpikeYOLO · VOC2007 | mAP@50-95: 31.9 -> 34.9 | Improved |
| add TDE (TCSA) to EMSYOLO | EMSYOLO · EvDET200K | mAP@50-95: 44.9 -> 47.1 | Improved |
| add TDE (TCSA) to Meta-SpikeFormer | Meta-SpikeFormer · VOC (VOC2007+VOC2012) | mAP@50-95: 24.3 -> 25.7 | Improved |
| replace TCSA attention with spike-driven attention (SDA) in TDE | SpikeYOLO · Attention energy (T=4, C=128, H=80, W=40) | energy (uJ): 2.18 E1 -> 5.24 E0 | Improved |
| replace TCSA with SDA in TDE | SpikeYOLO · VOC2007 | mAP@50: 55.9 -> 56.2 | Improved |
| replace TCSA with SDA in TDE | SpikeYOLO · EvDET200K | mAP@50-95: 47.6 -> 47.2 | Hurt |
| replace TCSA with SDA in TDE | EMSYOLO · VOC (VOC2007+VOC2012) | mAP@50: 77.1 -> 77.3 mAP@50; 50.8 -> 50.2 mAP@50-95 | Mixed |
Closest papers by meaning
- Brain-Inspired Spiking Neural Networks for Energy-Efficient Object Detection (CVPR 2025 · similarity 0.91)
- STAA-SNN: Spatial-Temporal Attention Aggregator for Spiking Neural Networks (CVPR 2025 · similarity 0.90)
- Gated Attention Coding for Training High-Performance and Efficient Spiking Neural Networks (AAAI 2024 · similarity 0.89)
- FSTA-SNN:Frequency-Based Spatial-Temporal Attention Module for Spiking Neural Networks (AAAI 2025 · similarity 0.89)
- Temporal Flexibility in Spiking Neural Networks: Towards Generalization Across Time Steps and Deployment Friendliness (ICLR 2025 · similarity 0.89)
- Training High Performance Spiking Neural Network by Temporal Model Calibration (ICML 2025 · similarity 0.89)
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.
