Diagnosing Convolutional Neural Networks using their Spectral Response
This provides a diagnostic tool for CNN practitioners to identify training problems like overfitting when validation data is unavailable, though it is incremental as it builds on existing spectral analysis methods.
The paper tackles the problem of diagnosing training issues in Convolutional Neural Networks (CNNs) by analyzing their spectral response, finding that high gain correlates with sensitivity to input perturbations and that gain fluctuations can indicate overfitting and learning rate problems, with experiments on ImageNet, MNIST, and CIFAR-10.
Convolutional Neural Networks (CNNs) are a class of artificial neural networks whose computational blocks use convolution, together with other linear and non-linear operations, to perform classification or regression. This paper explores the spectral response of CNNs and its potential use in diagnosing problems with their training. We measure the gain of CNNs trained for image classification on ImageNet and observe that the best models are also the most sensitive to perturbations of their input. Further, we perform experiments on MNIST and CIFAR-10 to find that the gain rises as the network learns and then saturates as the network converges. Moreover, we find that strong gain fluctuations can point to overfitting and learning problems caused by a poor choice of learning rate. We argue that the gain of CNNs can act as a diagnostic tool and potential replacement for the validation loss when hold-out validation data are not available.