# A Spiking Neural Network for Image Segmentation

arXiv: https://arxiv.org/abs/2106.08921 · HTML: https://mlsanity.com/paper/2106.08921/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 18 references that are in the map.
- First posted on arXiv 16 Jun 2021.

## Builds on (most cited first, 7 of 7)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Convolutional Neural Networks as a Model of the Visual System: Past, Present, and Future](https://mlsanity.com/paper/2001.07092/) (2020)
- [Benchmarking Keyword Spotting Efficiency on Neuromorphic Hardware](https://mlsanity.com/paper/1812.01739/) (2018)
- [Event-Driven Visual-Tactile Sensing and Learning for Robots](https://mlsanity.com/paper/2009.07083/) (2020)
- [Spiking Neural Network on Neuromorphic Hardware for Energy-Efficient Unidimensional SLAM](https://mlsanity.com/paper/1903.02504/) (2019)
- [NengoDL: Combining deep learning and neuromorphic modelling methods](https://mlsanity.com/paper/1805.11144/) (2018)
- [Neuromorphic Computing for Content-based Image Retrieval](https://mlsanity.com/paper/2008.01380/) (2020)

## Built on by (most cited first, 27 of 27)

- [SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligence](https://mlsanity.com/paper/2310.16620/) (2023)
- [Direct Learning-Based Deep Spiking Neural Networks: A Review](https://mlsanity.com/paper/2305.19725/) (2023)
- [Scaling Up Dynamic Graph Representation Learning via Spiking Neural Networks](https://mlsanity.com/paper/2208.10364/) (2022)
- [Spike2Former: Efficient Spiking Transformer for High-performance Image Segmentation](https://mlsanity.com/paper/2412.14587/) (2024)
- [Sneaky Spikes: Uncovering Stealthy Backdoor Attacks in Spiking Neural Networks with Neuromorphic Data](https://mlsanity.com/paper/2302.06279/) (2023)
- [Brain-inspired Multilayer Perceptron with Spiking Neurons](https://mlsanity.com/paper/2203.14679/) (2022)
- [Spike Calibration: Fast and Accurate Conversion of Spiking Neural Network for Object Detection and Segmentation](https://mlsanity.com/paper/2207.02702/) (2022)
- [Spiking Neural Network for Ultra-low-latency and High-accurate Object Detection](https://mlsanity.com/paper/2306.12010/) (2023)
- [Spiking neural networks for nonlinear regression](https://mlsanity.com/paper/2210.03515/) (2022)
- [Label Distribution Learning via Implicit Distribution Representation](https://mlsanity.com/paper/2209.13824/) (2022)
- [Efficient Event-Based Semantic Segmentation via Exploiting Frame-Event Fusion: A Hybrid Neural Network Approach](https://mlsanity.com/paper/2507.03765/) (2025)
- [Hybrid Spiking Neural Network Fine-tuning for Hippocampus Segmentation](https://mlsanity.com/paper/2302.07328/) (2023)
- [Deep Multi-Threshold Spiking-UNet for Image Processing](https://mlsanity.com/paper/2307.10974/) (2023)
- [Spiking Approximations of the MaxPooling Operation in Deep SNNs](https://mlsanity.com/paper/2205.07076/) (2022)
- [Energy-Efficient Deployment of Machine Learning Workloads on Neuromorphic Hardware](https://mlsanity.com/paper/2210.05006/) (2022)
- [Improvement of Spiking Neural Network with Bit Planes and Color Models](https://mlsanity.com/paper/2410.08229/) (2024)
- [Edge Intelligence with Spiking Neural Networks](https://mlsanity.com/paper/2507.14069/) (2025)
- [Exploring the Potentials of Spiking Neural Networks for Image Deraining](https://mlsanity.com/paper/2512.02258/) (2025)
- [Modern Neuromorphic AI: From Intra-Token to Inter-Token Processing](https://mlsanity.com/paper/2601.00245/) (2026)
- [Joint ANN-SNN Co-training for Object Localization and Image Segmentation](https://mlsanity.com/paper/2303.12738/) (2023)
- [A Deep Bayesian Convolutional Spiking Neural Network-based CAD system with Uncertainty Quantification for Medical Images Classification](https://mlsanity.com/paper/2504.17819/) (2025)
- [TDSNNs: Competitive Topographic Deep Spiking Neural Networks for Visual Cortex Modeling](https://mlsanity.com/paper/2508.04270/) (2025)
- [Reliable Brain Tumor Segmentation Based on Spiking Neural Networks with Efficient Training](https://mlsanity.com/paper/2601.16652/) (2026)
- [UIESNN: A Scale-Aware Spiking Network for Underwater Image Enhancement](https://mlsanity.com/paper/2605.08376/) (2026)
- [SpikeReg: Energy-Efficient 3D Deformable Medical Image Registration with Spiking Neural Networks](https://mlsanity.com/paper/2605.25144/) (2026)
- [Robust PnP on a Neuromorphic Processor for Object Pose Estimation](https://mlsanity.com/paper/2607.16834/) (2026)
- [Event-Frame Fusion for Inter-Frame Segmentation via Event-Guided Motion](https://mlsanity.com/paper/2609.22500/) (2026)

## Abstract (arXiv)

We seek to investigate the scalability of neuromorphic computing for computer vision, with the objective of replicating non-neuromorphic performance on computer vision tasks while reducing power consumption. We convert the deep Artificial Neural Network (ANN) architecture U-Net to a Spiking Neural Network (SNN) architecture using the Nengo framework. Both rate-based and spike-based models are trained and optimized for benchmarking performance and power, using a modified version of the ISBI 2D EM Segmentation dataset consisting of microscope images of cells. We propose a partitioning method to optimize inter-chip communication to improve speed and energy efficiency when deploying multi-chip networks on the Loihi neuromorphic chip. We explore the advantages of regularizing firing rates of Loihi neurons for converting ANN to SNN with minimum accuracy loss and optimized energy consumption. We propose a percentile based regularization loss function to limit the spiking rate of the neuron between a desired range. The SNN is converted directly from the corresponding ANN, and demonstrates similar semantic segmentation as the ANN using the same number of neurons and weights. However, the neuromorphic implementation on the Intel Loihi neuromorphic chip is over 2x more energy-efficient than conventional hardware (CPU, GPU) when running online (one image at a time). These power improvements are achieved without sacrificing the task performance accuracy of the network, and when all weights (Loihi, CPU, and GPU networks) are quantized to 8 bits.