Negative Log Likelihood Ratio Loss for Deep Neural Network Classification
This addresses classification accuracy for deep learning practitioners, but appears incremental as it modifies an existing loss function.
The authors tackled the problem of classification in deep neural networks by proposing a discriminative loss function based on the negative log likelihood ratio between correct and competing classes, which significantly outperformed the cross-entropy loss on the CIFAR-10 image classification task.
In deep neural network, the cross-entropy loss function is commonly used for classification. Minimizing cross-entropy is equivalent to maximizing likelihood under assumptions of uniform feature and class distributions. It belongs to generative training criteria which does not directly discriminate correct class from competing classes. We propose a discriminative loss function with negative log likelihood ratio between correct and competing classes. It significantly outperforms the cross-entropy loss on the CIFAR-10 image classification task.