Neuromorphic object recognition with spiking neural networks (SNNs) is the
cornerstone of low-power neuromorphic computing. However, existing SNNs suffer
from significant latency, utilizing 10 to 40 timesteps or more, to recognize
neuromorphic objects. At low latencies, the performance of existing SNNs is
drastically degraded. In this work, we propose the Shrinking SNN (SSNN) to
achieve low-latency neuromorphic object recognition without reducing
performance. Concretely, we alleviate the temporal redundancy in SNNs by
dividing SNNs into multiple stages with progressively shrinking timesteps,
which significantly reduces the inference latency. During timestep shrinkage,
the temporal transformer smoothly transforms the temporal scale and preserves
the information maximally. Moreover, we add multiple early classifiers to the
SNN during training to mitigate the mismatch between the surrogate gradient and
the true gradient, as well as the gradient vanishing/exploding, thus
eliminating the performance degradation at low latency. Extensive experiments
on neuromorphic datasets, CIFAR10-DVS, N-Caltech101, and DVS-Gesture have
revealed that SSNN is able to improve the baseline accuracy by 6.55% ~ 21.41%.
With only 5 average timesteps and without any data augmentation, SSNN is able
to achieve an accuracy of 73.63% on CIFAR10-DVS. This work presents a
heterogeneous temporal scale SNN and provides valuable insights into the
development of high-performance, low-latency SNNs.

通过将 SNN 拆分为多个阶段，并逐渐减小时间步长，本研究提出了 Shrinking SNN (SSNN) 来实现低延迟的神经形态学物体识别。SSNN 能够显著降低推理延迟，并通过引入多个早期分类器来消除低延迟下性能的退化。实验证明，在多个神经形态学数据集上，SSNN 能够将基准准确度提高 6.55% ~ 21.41%。在 CIFAR10-DVS 数据集上，SSNN 只需 5 个平均时间步长且无需任何数据增强即可达到 73.63% 的准确度。本研究提出了一个具有异构时间尺度的 SNN，并对高性能、低延迟 SNN 的发展提供了有价值的见解。