论文标题
自适应蜘蛛网：使用具有可学习神经元动力学的尖峰神经网络的基于事件的光流估计
Adaptive-SpikeNet: Event-based Optical Flow Estimation using Spiking Neural Networks with Learnable Neuronal Dynamics
论文作者
论文摘要
基于事件的摄像机最近由于其不同步捕获时间丰富的信息的能力而显示出高速运动估计的巨大潜力。具有神经启发的事件驱动的处理的尖峰神经网络（SNN）可以有效地处理异步数据，而神经元模型（例如泄漏的综合和火灾（LIF））可以跟踪输入中包含的典型时序信息。 SNN通过在神经元内存中保持动态状态，保留重要信息，同时忘记冗余数据随着时间的推移而实现这一目标。因此，我们认为，与类似尺寸的模拟神经网络（ANN）相比，SNN将允许在顺序回归任务上更好地性能。但是，由于以后的层消失，很难训练深的SNN。为此，我们提出了一个具有可学习的神经元动力学的自适应完全刺激框架，以减轻尖峰消失的问题。我们通过时间（BPTT）利用基于替代梯度的反向传播来训练我们的深SNN。我们验证了在多车立体观察相机（MVSEC）数据集和DSEC-FLOW数据集上的光流估计任务的方法。我们在这些数据集上的实验显示，与最新的ANN相比，平均终点误差（AEE）平均降低了13％。我们还探索了几种缩小的模型，并观察到我们的SNN模型始终超过尺寸的ANN，提供10％-16％的AEE。这些结果证明了SNN对较小模型的重要性及其在边缘的适用性。在效率方面，我们的SNN可为网络参数（48.3倍）和计算能量（10.2倍）节省大量节省，而与最新的ANN实现相比，EPE的EPE降低了约10％。
Event-based cameras have recently shown great potential for high-speed motion estimation owing to their ability to capture temporally rich information asynchronously. Spiking Neural Networks (SNNs), with their neuro-inspired event-driven processing can efficiently handle such asynchronous data, while neuron models such as the leaky-integrate and fire (LIF) can keep track of the quintessential timing information contained in the inputs. SNNs achieve this by maintaining a dynamic state in the neuron memory, retaining important information while forgetting redundant data over time. Thus, we posit that SNNs would allow for better performance on sequential regression tasks compared to similarly sized Analog Neural Networks (ANNs). However, deep SNNs are difficult to train due to vanishing spikes at later layers. To that effect, we propose an adaptive fully-spiking framework with learnable neuronal dynamics to alleviate the spike vanishing problem. We utilize surrogate gradient-based backpropagation through time (BPTT) to train our deep SNNs from scratch. We validate our approach for the task of optical flow estimation on the Multi-Vehicle Stereo Event-Camera (MVSEC) dataset and the DSEC-Flow dataset. Our experiments on these datasets show an average reduction of 13% in average endpoint error (AEE) compared to state-of-the-art ANNs. We also explore several down-scaled models and observe that our SNN models consistently outperform similarly sized ANNs offering 10%-16% lower AEE. These results demonstrate the importance of SNNs for smaller models and their suitability at the edge. In terms of efficiency, our SNNs offer substantial savings in network parameters (48.3x) and computational energy (10.2x) while attaining ~10% lower EPE compared to the state-of-the-art ANN implementations.
