# DIET-SNN: Direct Input Encoding With Leakage and Threshold Optimization in Deep Spiking Neural Networks

arXiv: https://arxiv.org/abs/2008.03658 · HTML: https://mlsanity.com/paper/2008.03658/

## Key facts

- Cited by 71 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Aug 2020.

## Built on by (most cited first, 30 of 71)

- [Spikformer: When Spiking Neural Network Meets Transformer](https://mlsanity.com/paper/2209.15425/) (2022)
- [Temporal Efficient Training of Spiking Neural Network via Gradient Re-weighting](https://mlsanity.com/paper/2202.11946/) (2022)
- [A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibration](https://mlsanity.com/paper/2106.06984/) (2021)
- [Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representation](https://mlsanity.com/paper/2205.00459/) (2022)
- [HIRE-SNN: Harnessing the Inherent Robustness of Energy-Efficient Deep Spiking Neural Networks by Training with Crafted Input Noise](https://mlsanity.com/paper/2110.11417/) (2021)
- [GLIF: A Unified Gated Leaky Integrate-and-Fire Neuron for Spiking Neural Networks](https://mlsanity.com/paper/2210.13768/) (2022)
- [Beyond Classification: Directly Training Spiking Neural Networks for Semantic Segmentation](https://mlsanity.com/paper/2110.07742/) (2021)
- [Neuromorphic Data Augmentation for Training Spiking Neural Networks](https://mlsanity.com/paper/2203.06145/) (2022)
- [Ternary Spike: Learning Ternary Spikes for Spiking Neural Networks](https://mlsanity.com/paper/2312.06372/) (2023)
- [Joint A-SNN: Joint Training of Artificial and Spiking Neural Networks via Self-Distillation and Weight Factorization](https://mlsanity.com/paper/2305.02099/) (2023)
- [Membrane Potential Batch Normalization for Spiking Neural Networks](https://mlsanity.com/paper/2308.08359/) (2023)
- [Spiking PointNet: Spiking Neural Networks for Point Clouds](https://mlsanity.com/paper/2310.06232/) (2023)
- [Direct Learning-Based Deep Spiking Neural Networks: A Review](https://mlsanity.com/paper/2305.19725/) (2023)
- [Spikformer V2: Join the High Accuracy Club on ImageNet with an SNN Ticket](https://mlsanity.com/paper/2401.02020/) (2024)
- [RMP-Loss: Regularizing Membrane Potential Distribution for Spiking Neural Networks](https://mlsanity.com/paper/2308.06787/) (2023)
- [Training Full Spike Neural Networks via Auxiliary Accumulation Pathway](https://mlsanity.com/paper/2301.11929/) (2023)
- [Hybrid SNN-ANN: Energy-Efficient Classification and Object Detection for Event-Based Vision](https://mlsanity.com/paper/2112.03423/) (2021)
- [Real Spike: Learning Real-valued Spikes for Spiking Neural Networks](https://mlsanity.com/paper/2210.06686/) (2022)
- [Exploiting Noise as a Resource for Computation and Learning in Spiking Neural Networks](https://mlsanity.com/paper/2305.16044/) (2023)
- [One Timestep is All You Need: Training Spiking Neural Networks with Ultra Low Latency](https://mlsanity.com/paper/2110.05929/) (2021)
- [Spike Calibration: Fast and Accurate Conversion of Spiking Neural Network for Object Detection and Segmentation](https://mlsanity.com/paper/2207.02702/) (2022)
- [Take A Shortcut Back: Mitigating the Gradient Vanishing for Training Spiking Neural Networks](https://mlsanity.com/paper/2401.04486/) (2024)
- [Spiking Transformer:Introducing Accurate Addition-Only Spiking Self-Attention for Transformer](https://mlsanity.com/paper/2503.00226/) (2025)
- [Uncovering the Representation of Spiking Neural Networks Trained with Surrogate Gradient](https://mlsanity.com/paper/2304.13098/) (2023)
- [Temporal Knowledge Sharing enable Spiking Neural Network Learning from Past and Future](https://mlsanity.com/paper/2304.06540/) (2023)
- [Enhancing the Performance of Transformer-based Spiking Neural Networks by SNN-optimized Downsampling with Precise Gradient Backpropagation](https://mlsanity.com/paper/2305.05954/) (2023)
- [Can Deep Neural Networks be Converted to Ultra Low-Latency Spiking Neural Networks?](https://mlsanity.com/paper/2112.12133/) (2021)
- [Towards Low-Latency Energy-Efficient Deep SNNs via Attention-Guided Compression](https://mlsanity.com/paper/2107.12445/) (2021)
- [In-Sensor & Neuromorphic Computing are all you need for Energy Efficient Computer Vision](https://mlsanity.com/paper/2212.10881/) (2022)
- [MT-SNN: Enhance Spiking Neural Network with Multiple Thresholds](https://mlsanity.com/paper/2303.11127/) (2023)

## Abstract (arXiv)

Bio-inspired spiking neural networks (SNNs), operating with asynchronous binary signals (or spikes) distributed over time, can potentially lead to greater computational efficiency on event-driven hardware. The state-of-the-art SNNs suffer from high inference latency, resulting from inefficient input encoding, and sub-optimal settings of the neuron parameters (firing threshold, and membrane leak). We propose DIET-SNN, a low-latency deep spiking network that is trained with gradient descent to optimize the membrane leak and the firing threshold along with other network parameters (weights). The membrane leak and threshold for each layer of the SNN are optimized with end-to-end backpropagation to achieve competitive accuracy at reduced latency. The analog pixel values of an image are directly applied to the input layer of DIET-SNN without the need to convert to spike-train. The first convolutional layer is trained to convert inputs into spikes where leaky-integrate-and-fire (LIF) neurons integrate the weighted inputs and generate an output spike when the membrane potential crosses the trained firing threshold. The trained membrane leak controls the flow of input information and attenuates irrelevant inputs to increase the activation sparsity in the convolutional and dense layers of the network. The reduced latency combined with high activation sparsity provides large improvements in computational efficiency. We evaluate DIET-SNN on image classification tasks from CIFAR and ImageNet datasets on VGG and ResNet architectures. We achieve top-1 accuracy of 69% with 5 timesteps (inference latency) on the ImageNet dataset with 12x less compute energy than an equivalent standard ANN. Additionally, DIET-SNN performs 20-500x faster inference compared to other state-of-the-art SNN models.