Research map / Architectures and efficiency / Spiking networks
Rethinking SNN Online Training and Deployment: Gradient-Coherent Learning via Hybrid-Driven LIF Model
Zecheng Hao, Yifan Huang, Zijie Xu, Wenxuan Liu, Yuanhong Tang, Zhaofei Yu, Tiejun Huang
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 |
|---|---|---|---|
| replace LIF with HD-LIF in online training (ablation) | online SNN training, ResNet-18 · CIFAR-100 ablation config | accuracy (%): 71.75 -> 80.16 | Improved |
| compress firing spikes to 4 bits (ablation) | HD-LIF · CIFAR-100 ablation config | energy (mJ): 0.26 -> 0.03 (accuracy 80.16 -> 79.62) | Improved |
| use Parallel HD-LIF in 50% of layers (ablation) | HD-LIF · CIFAR-100 ablation config | NOPs (M): 6.59 -> 4.62 | Improved |
| use Parallel HD-LIF in 50% of layers (ablation) | HD-LIF · CIFAR-100 ablation config | accuracy (%): 80.16 -> 78.82 | Hurt |
| add Mem-BN and SECA attention (ablation) | HD-LIF ResNet-18 · CIFAR-10 | accuracy (%): 95.59 -> 95.91 | Improved |
| add Mem-BN and SECA attention (ablation) | HD-LIF ResNet-18 · CIFAR-100 | accuracy (%): 78.45 -> 79.33 | Improved |
| add Mem-BN and SECA attention (ablation) | HD-LIF ResNet-18 · DVS-CIFAR10 | accuracy (%): 81.70 -> 83.50 | Improved |
| use HD-LIF with 4-bit spikes and weight compression instead of online SLTT | ResNet-18 online training · CIFAR-100 | accuracy (%): 74.38 -> 78.45 | Improved |
| use HD-LIF instead of OTTT/SLTT online training | ResNet-34 · ImageNet-1k | accuracy (%): 66.19 -> 69.77 | Improved |
Closest papers by meaning
- Enhancing Training of Spiking Neural Network with Stochastic Latency (AAAI 2024 · similarity 0.88)
- CLIF: Complementary Leaky Integrate-and-Fire Neuron for Spiking Neural Networks (ICML 2024 · similarity 0.88)
- NDOT: Neuronal Dynamics-based Online Training for Spiking Neural Networks (ICML 2024 · similarity 0.87)
- EnOF-SNN: Training Accurate Spiking Neural Networks via Enhancing the Output Feature (NeurIPS 2024 · similarity 0.87)
- LM-HT SNN: Enhancing the Performance of SNN to ANN Counterpart through Learnable Multi-hierarchical Threshold Model (NeurIPS 2024 · similarity 0.87)
- Enhanced Self-Distillation Framework for Efficient Spiking Neural Network Training (NeurIPS 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.
