StereoSpike: Depth Learning with a Spiking Neural Network
arXiv:2109.13751 · doi:10.1109/ACCESS.2022.3226484
Abstract
Depth estimation is an important computer vision task, useful in particular for navigation in autonomous vehicles, or for object manipulation in robotics. Here we solved it using an end-to-end neuromorphic approach, combining two event-based cameras and a Spiking Neural Network (SNN) with a slightly modified U-Net-like encoder-decoder architecture, that we named StereoSpike. More specifically, we used the Multi Vehicle Stereo Event Camera Dataset (MVSEC). It provides a depth ground-truth, which was used to train StereoSpike in a supervised manner, using surrogate gradient descent. We propose a novel readout paradigm to obtain a dense analog prediction -- the depth of each pixel -- from the spikes of the decoder. We demonstrate that this architecture generalizes very well, even better than its non-spiking counterparts, leading to state-of-the-art test accuracy. To the best of our knowledge, it is the first time that such a large-scale regression problem is solved by a fully spiking network. Finally, we show that low firing rates (<10%) can be obtained via regularization, with a minimal cost in accuracy. This means that StereoSpike could be efficiently implemented on neuromorphic chips, opening the door for low power and real time embedded systems.
References in corpus (6)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Event-based Vision: A Survey
- Deep Residual Learning in Spiking Neural Networks
- Learning to Detect Objects with a 1 Megapixel Event Camera
- Self-Supervised Learning of Event-Based Optical Flow with Spiking Neural Networks
- Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networks