ScieNet: Deep Learning with Spike-assisted Contextual Information Extraction
This addresses reliability issues for systems like autonomous vehicles and robotics that face imperfect inputs, though it appears incremental as it builds on existing DNN and SNN methods.
The paper tackles the problem of deep neural networks' performance degradation under input perturbations by proposing ScieNet, a hybrid architecture that integrates spiking neural networks for contextual information extraction with back-end DNNs for classification. It demonstrates significant accuracy improvements on noisy and rainy CIFAR images without prior training on perturbed inputs, while maintaining state-of-the-art accuracy on clean images.
Deep neural networks (DNNs) provide high image classification accuracy, but experience significant performance degradation when perturbation from various sources are present in the input. The lack of resilience to input perturbations makes DNN less reliable for systems interacting with physical world such as autonomous vehicles, robotics, to name a few, where imperfect input is the normal condition. We present a hybrid deep network architecture with spike-assisted contextual information extraction (ScieNet). ScieNet integrates unsupervised learning using spiking neural network (SNN) for unsupervised contextual informationextraction with a back-end DNN trained for classification. The integrated network demonstrates high resilience to input perturbations without relying on prior training on perturbed inputs. We demonstrate ScieNet with different back-end DNNs for image classification using CIFAR dataset considering stochastic (noise) and structured (rain) input perturbations. Experimental results demonstrate significant improvement in accuracy on noisy and rainy images without prior training, while maintaining state-of-the-art accuracy on clean images.