A novel multi-scale loss function for classification problems in machine learning
This work addresses classification accuracy issues in machine learning, but it appears incremental as it builds upon existing loss functions without a major paradigm shift.
The authors tackled the problem of improving classification performance by introducing a novel two-scale loss function that focuses training on poorly classified objects, resulting in increased performance metrics compared to cross-entropy on MNIST, CIFAR10, and CIFAR100 datasets.
We introduce two-scale loss functions for use in various gradient descent algorithms applied to classification problems via deep neural networks. This new method is generic in the sense that it can be applied to a wide range of machine learning architectures, from deep neural networks to support vector machines for example. These two-scale loss functions allow to focus the training onto objects in the training set which are not well classified. This leads to an increase in several measures of performance for appropriately-defined two-scale loss functions with respect to the more classical cross-entropy when tested on traditional deep neural networks on the MNIST, CIFAR10, and CIFAR100 data-sets.