Threshold Modulation for Online Test-Time Adaptation of Spiking Neural Networks
Not on the map. Why?
Abstract (arXiv)
Recently, spiking neural networks (SNNs), deployed on neuromorphic chips, provide highly efficient solutions on edge devices in different scenarios. However, their ability to adapt to distribution shifts after deployment has become a crucial challenge. Online test-time adaptation (OTTA) offers a promising solution by enabling models to dynamically adjust to new data distributions without requiring source data or labeled target samples. Nevertheless, existing OTTA methods are largely designed for traditional artificial neural networks and are not well-suited for SNNs. To address this gap, we propose a low-power, neuromorphic chip-friendly online test-time adaptation framework, aiming to enhance model generalization under distribution shifts. The proposed approach is called Threshold Modulation (TM), which dynamically adjusts the firing threshold through neuronal dynamics-inspired normalization, being more compatible with neuromorphic hardware. Experimental results on benchmark datasets demonstrate the effectiveness of this method in improving the robustness of SNNs against distribution shifts while maintaining low computational cost. The proposed method offers a practical solution for online test-time adaptation of SNNs, providing inspiration for the design of future neuromorphic chips. The demo code is available at github.com/NneurotransmitterR/TM-OTTA-SNN.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 34 of its 54 references that are in the map. First posted on arXiv 8 May 2025.
Builds on
34 of 54 references.
References · 34
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
- 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
- 2015Domain-Adversarial Training of Neural Networkscited by 3,044
- 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
- 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 901
- 2019Surrogate Gradient Learning in Spiking Neural Networkscited by 626
- 2022Continual Test-Time Domain Adaptationcited by 525
- 2022Efficient Test-Time Model Adaptation without Forgettingcited by 469
- 2020Improving robustness against common corruptions by covariate shift adaptationcited by 431
- 2023Towards Stable Test-Time Adaptation in Dynamic Wild Worldcited by 415
- 2017Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscited by 406
22 more
- 2020Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networkscited by 345
- 2021Deep Residual Learning in Spiking Neural Networkscited by 331
- 2020Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shiftcited by 236
- 2018Direct Training for Spiking Neural Networks: Faster, Larger, Bettercited by 233
- 2022Parameter-free Online Test-time Adaptationcited by 189
- 2018Long short-term memory and learning-to-learn in networks of spiking neuronscited by 181
- 2023SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligencecited by 169
- 2022NOTE: Robust Continual Test-time Adaptation Against Temporal Correlationcited by 151
- 2021The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalizationcited by 131
- 2024Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factorscited by 106
- 2022Object Detection with Spiking Neural Networks on Automotive Event Datacited by 80
- 2016Convolutional Networks for Fast, Energy-Efficient Neuromorphic Computingcited by 70
- 2022Test-Time Adaptation via Self-Training with Nearest Neighbor Informationcited by 64
- 2023Speck: A Smart event-based Vision Sensor with a low latency 327K Neuron Convolutional Neuronal Network Processing Pipelinecited by 52
- 2023Towards Memory- and Time-Efficient Backpropagation for Training Spiking Neural Networkscited by 37
- 2022ReckOn: A 28nm Sub-mm2 Task-Agnostic Spiking Recurrent Neural Network Processor Enabling On-Chip Learning over Second-Long Timescalescited by 35
- 2023Membrane Potential Batch Normalization for Spiking Neural Networkscited by 35
- 2020Convolutional Spiking Neural Networks for Spatio-Temporal Feature Extractioncited by 23
- 2023Neuro-Modulated Hebbian Learning for Fully Test-Time Adaptationcited by 23
- 2023Darwin3: A large-scale neuromorphic chip with a Novel ISA and On-Chip Learningcited by 22
- 2024Brain-Inspired Online Adaptation for Remote Sensing with Spiking Neural Networkcited by 8
- 2024Toward Large-scale Spiking Neural Networks: A Comprehensive Survey and Future Directionscited by 7
Built on by
Citing papers per year: 2026: 1.
1 paper.