A low-rank tensor reconstruction and denoising method for enhancing CNN performance

Neural network training data is often corrupted by equipment malfunction or noise leading to red blurry and incomplete data. This paper proposes a combination of a reconstruction technique and a neural network to deal with data corruption in a machine vision task. Specifically, we consider minimizing the tensor nuclear norm for low-rank data completion and denoising and demonstrate the method's effectiveness using a convolutional neural network (CNN) for image classification. We conduct classification experiments on 3 datasets, showing consistently that training on reconstructed images achieves improved accuracy ranging from 7-25% over training using corrupted data.