Detection of out-of-distribution samples using binary neuron activation patterns
This addresses a critical limitation in safety-critical applications like self-driving cars, but it is an incremental improvement over existing OOD detection methods.
The paper tackles the problem of out-of-distribution (OOD) sample detection in deep neural networks by introducing a method based on binary neuron activation patterns, achieving high performance across multiple architectures and datasets.
Deep neural networks (DNN) have outstanding performance in various applications. Despite numerous efforts of the research community, out-of-distribution (OOD) samples remain a significant limitation of DNN classifiers. The ability to identify previously unseen inputs as novel is crucial in safety-critical applications such as self-driving cars, unmanned aerial vehicles, and robots. Existing approaches to detect OOD samples treat a DNN as a black box and evaluate the confidence score of the output predictions. Unfortunately, this method frequently fails, because DNNs are not trained to reduce their confidence for OOD inputs. In this work, we introduce a novel method for OOD detection. Our method is motivated by theoretical analysis of neuron activation patterns (NAP) in ReLU-based architectures. The proposed method does not introduce a high computational overhead due to the binary representation of the activation patterns extracted from convolutional layers. The extensive empirical evaluation proves its high performance on various DNN architectures and seven image datasets.