论文标题
使用二进制神经元激活模式检测分布样品
Detection of out-of-distribution samples using binary neuron activation patterns
论文作者
论文摘要
深神经网络（DNN）在各种应用中都具有出色的性能。尽管研究界做出了许多努力，但分布式（OOD）样本仍然是DNN分类器的重要限制。在安全至关重要的应用中，例如自动驾驶汽车，无人驾驶飞机和机器人，可以识别以前看不见的投入为新颖的投入至关重要。现有的检测OOD样品的方法将DNN视为黑匣子，并评估输出预测的置信度评分。不幸的是，这种方法经常失败，因为DNN没有受过训练以降低其对OOD输入的信心。在这项工作中，我们引入了一种新颖的OOD检测方法。我们的方法是由基于RELU的架构中神经元激活模式（NAP）的理论分析激励的。由于从卷积层提取的激活模式的二进制表示，该方法不会引入高计算开销。广泛的经验评估证明了其在各种DNN架构和七个图像数据集上的高性能。
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.
