Learning Event-based Spatio-Temporal Feature Descriptors via Local Synaptic Plasticity: A Biologically-Plausible Perspective of Computer Vision. (arXiv:2111.00791v3 [cs.CV] UPDATED)

We present an optimization-based theory describing spiking cortical ensembles
equipped with Spike-Timing-Dependent Plasticity (STDP) learning, as empirically
observed in the visual cortex. Using our methods, we build a class of
fully-connected, convolutional and action-based feature descriptors for
event-based camera that we respectively assess on N-MNIST, challenging
CIFAR10-DVS and on the IBM DVS128 gesture dataset. We report significant
accuracy improvements compared to conventional state-of-the-art event-based
feature descriptors (+8% on CIFAR10-DVS). We report large improvements in
accuracy compared to state-of-the-art STDP-based systems …

arxiv computer vision cv event learning perspective vision