Effective Out-of-Distribution Detection in Classifier Based on PEDCC-Loss
This addresses security concerns in AI by improving OOD detection for classifiers, but it appears incremental as it builds on existing PEDCC methods.
The paper tackles the problem of overconfidence in deep neural networks for out-of-distribution (OOD) detection by proposing an algorithm based on PEDCC-Loss, which achieves better OOD detection performance without input preprocessing and reduces computational burden.
Deep neural networks suffer from the overconfidence issue in the open world, meaning that classifiers could yield confident, incorrect predictions for out-of-distribution (OOD) samples. Thus, it is an urgent and challenging task to detect these samples drawn far away from training distribution based on the security considerations of artificial intelligence. Many current methods based on neural networks mainly rely on complex processing strategies, such as temperature scaling and input preprocessing, to obtain satisfactory results. In this paper, we propose an effective algorithm for detecting out-of-distribution examples utilizing PEDCC-Loss. We mathematically analyze the nature of the confidence score output by the PEDCC (Predefined Evenly-Distribution Class Centroids) classifier, and then construct a more effective scoring function to distinguish in-distribution (ID) and out-of-distribution. In this method, there is no need to preprocess the input samples and the computational burden of the algorithm is reduced. Experiments demonstrate that our method can achieve better OOD detection performance.