Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.16338 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914402006990848 |
|---|---|
| author | Vaillant, Maxime Carlier, Axel Ng, Lai Xing Hurter, Christophe Cottereau, Benoit R. |
| author_facet | Vaillant, Maxime Carlier, Axel Ng, Lai Xing Hurter, Christophe Cottereau, Benoit R. |
| contents | Event-based vision sensors provide significant advantages for high-speed perception, including microsecond temporal resolution, high dynamic range, and low power consumption. When combined with Spiking Neural Networks (SNNs), they can be deployed on neuromorphic hardware, enabling energy-efficient applications on embedded systems. However, this potential is severely limited by the scarcity of large-scale labeled datasets required to effectively train such models. In this work, we introduce SpikeCLR, a contrastive self-supervised learning framework that enables SNNs to learn robust visual representations from unlabeled event data. We adapt prior frame-based methods to the spiking domain using surrogate gradient training and introduce a suite of event-specific augmentations that leverage spatial, temporal, and polarity transformations. Through extensive experiments on CIFAR10-DVS, N-Caltech101, N-MNIST, and DVS-Gesture benchmarks, we demonstrate that self-supervised pretraining with subsequent fine-tuning outperforms supervised learning in low-data regimes, achieving consistent gains in few-shot and semi-supervised settings. Our ablation studies reveal that combining spatial and temporal augmentations is critical for learning effective spatio-temporal invariances in event data. We further show that learned representations transfer across datasets, contributing to efforts for powerful event-based models in label-scarce settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_16338 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SpikeCLR: Contrastive Self-Supervised Learning for Few-Shot Event-Based Vision using Spiking Neural Networks Vaillant, Maxime Carlier, Axel Ng, Lai Xing Hurter, Christophe Cottereau, Benoit R. Computer Vision and Pattern Recognition Event-based vision sensors provide significant advantages for high-speed perception, including microsecond temporal resolution, high dynamic range, and low power consumption. When combined with Spiking Neural Networks (SNNs), they can be deployed on neuromorphic hardware, enabling energy-efficient applications on embedded systems. However, this potential is severely limited by the scarcity of large-scale labeled datasets required to effectively train such models. In this work, we introduce SpikeCLR, a contrastive self-supervised learning framework that enables SNNs to learn robust visual representations from unlabeled event data. We adapt prior frame-based methods to the spiking domain using surrogate gradient training and introduce a suite of event-specific augmentations that leverage spatial, temporal, and polarity transformations. Through extensive experiments on CIFAR10-DVS, N-Caltech101, N-MNIST, and DVS-Gesture benchmarks, we demonstrate that self-supervised pretraining with subsequent fine-tuning outperforms supervised learning in low-data regimes, achieving consistent gains in few-shot and semi-supervised settings. Our ablation studies reveal that combining spatial and temporal augmentations is critical for learning effective spatio-temporal invariances in event data. We further show that learned representations transfer across datasets, contributing to efforts for powerful event-based models in label-scarce settings. |
| title | SpikeCLR: Contrastive Self-Supervised Learning for Few-Shot Event-Based Vision using Spiking Neural Networks |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.16338 |