Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.02298 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915501862551552 |
|---|---|
| author | Luo, Xinyu Chen, Kecheng Sun, Pao-Sheng Vincent Tian, Chris Xing Basu, Arindam Li, Haoliang |
| author_facet | Luo, Xinyu Chen, Kecheng Sun, Pao-Sheng Vincent Tian, Chris Xing Basu, Arindam Li, Haoliang |
| contents | Spiking Neural Networks (SNNs), as a biologically plausible alternative to Artificial Neural Networks (ANNs), have demonstrated advantages in terms of energy efficiency, temporal processing, and biological plausibility. However, SNNs are highly sensitive to distribution shifts, which can significantly degrade their performance in real-world scenarios. Traditional test-time adaptation (TTA) methods designed for ANNs often fail to address the unique computational dynamics of SNNs, such as sparsity and temporal spiking behavior. To address these challenges, we propose SPike-Aware Consistency Enhancement (SPACE), the first source-free and single-instance TTA method specifically designed for SNNs. SPACE leverages the inherent spike dynamics of SNNs to maximize the consistency of spike-behavior-based local feature maps across augmented versions of a single test sample, enabling robust adaptation without requiring source data. We evaluate SPACE on multiple datasets. Furthermore, SPACE exhibits robust generalization across diverse network architectures, consistently enhancing the performance of SNNs on CNNs, Transformer, and ConvLSTM architectures. Experimental results show that SPACE outperforms state-of-the-art ANN methods while maintaining lower computational cost, highlighting its effectiveness and robustness for SNNs in real-world settings. The code will be available at https://github.com/ethanxyluo/SPACE. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_02298 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SPACE: SPike-Aware Consistency Enhancement for Test-Time Adaptation in Spiking Neural Networks Luo, Xinyu Chen, Kecheng Sun, Pao-Sheng Vincent Tian, Chris Xing Basu, Arindam Li, Haoliang Machine Learning Spiking Neural Networks (SNNs), as a biologically plausible alternative to Artificial Neural Networks (ANNs), have demonstrated advantages in terms of energy efficiency, temporal processing, and biological plausibility. However, SNNs are highly sensitive to distribution shifts, which can significantly degrade their performance in real-world scenarios. Traditional test-time adaptation (TTA) methods designed for ANNs often fail to address the unique computational dynamics of SNNs, such as sparsity and temporal spiking behavior. To address these challenges, we propose SPike-Aware Consistency Enhancement (SPACE), the first source-free and single-instance TTA method specifically designed for SNNs. SPACE leverages the inherent spike dynamics of SNNs to maximize the consistency of spike-behavior-based local feature maps across augmented versions of a single test sample, enabling robust adaptation without requiring source data. We evaluate SPACE on multiple datasets. Furthermore, SPACE exhibits robust generalization across diverse network architectures, consistently enhancing the performance of SNNs on CNNs, Transformer, and ConvLSTM architectures. Experimental results show that SPACE outperforms state-of-the-art ANN methods while maintaining lower computational cost, highlighting its effectiveness and robustness for SNNs in real-world settings. The code will be available at https://github.com/ethanxyluo/SPACE. |
| title | SPACE: SPike-Aware Consistency Enhancement for Test-Time Adaptation in Spiking Neural Networks |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2504.02298 |