# Razor SNN: Efficient Spiking Neural Network with Temporal Embeddings

arXiv: https://arxiv.org/abs/2306.17597 · HTML: https://mlsanity.com/paper/2306.17597/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 30 references that are in the map.
- First posted on arXiv 30 Jun 2023.

## Builds on (most cited first, 15 of 15)

- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks](https://mlsanity.com/paper/1706.02609/) (2017)
- [Going Deeper With Directly-Trained Larger Spiking Neural Networks](https://mlsanity.com/paper/2011.05280/) (2020)
- [Direct Training for Spiking Neural Networks: Faster, Larger, Better](https://mlsanity.com/paper/1809.05793/) (2018)
- [Training Deep Spiking Neural Networks using Backpropagation](https://mlsanity.com/paper/1608.08782/) (2016)
- [The Heidelberg spiking datasets for the systematic evaluation of spiking neural networks](https://mlsanity.com/paper/1910.07407/) (2019)
- [Temporal-wise Attention Spiking Neural Networks for Event Streams Classification](https://mlsanity.com/paper/2107.11711/) (2021)
- [LIAF-Net: Leaky Integrate and Analog Fire Network for Lightweight and Efficient Spatiotemporal Information Processing](https://mlsanity.com/paper/2011.06176/) (2020)
- [DART: Distribution Aware Retinal Transform for Event-based Cameras](https://mlsanity.com/paper/1710.10800/) (2017)
- [Distilling Spikes: Knowledge Distillation in Spiking Neural Networks](https://mlsanity.com/paper/2005.00288/) (2020)
- [Attention Mechanisms for Object Recognition with Event-Based Cameras](https://mlsanity.com/paper/1807.09480/) (2018)
- [Towards Low-Latency Energy-Efficient Deep SNNs via Attention-Guided Compression](https://mlsanity.com/paper/2107.12445/) (2021)
- [Avatar Knowledge Distillation: Self-ensemble Teacher Paradigm with Uncertainty](https://mlsanity.com/paper/2305.02722/) (2023)
- [Closing the Accuracy Gap in an Event-Based Visual Recognition Task](https://mlsanity.com/paper/1906.08859/) (2019)
- [Distilling Neuron Spike with High Temperature in Reinforcement Learning Agents](https://mlsanity.com/paper/2108.10078/) (2021)

## Built on by (most cited first, 2 of 2)

- [ClearSight: Human Vision-Inspired Solutions for Event-Based Motion Deblurring](https://mlsanity.com/paper/2501.15808/) (2025)
- [SpikeGen: Decoupled "Rods and Cones" Visual Representation Processing with Latent Generative Framework](https://mlsanity.com/paper/2505.18049/) (2025)

## Abstract (arXiv)

The event streams generated by dynamic vision sensors (DVS) are sparse and non-uniform in the spatial domain, while still dense and redundant in the temporal domain. Although spiking neural network (SNN), the event-driven neuromorphic model, has the potential to extract spatio-temporal features from the event streams, it is not effective and efficient. Based on the above, we propose an events sparsification spiking framework dubbed as Razor SNN, pruning pointless event frames progressively. Concretely, we extend the dynamic mechanism based on the global temporal embeddings, reconstruct the features, and emphasize the events effect adaptively at the training stage. During the inference stage, eliminate fruitless frames hierarchically according to a binary mask generated by the trained temporal embeddings. Comprehensive experiments demonstrate that our Razor SNN achieves competitive performance consistently on four events-based benchmarks: DVS 128 Gesture, N-Caltech 101, CIFAR10-DVS and SHD.