Model2Detector：利用少量梯度步长拓宽分布外检测的信息瓶颈
Model2Detector: Widening the Information Bottleneck for Out-of-Distribution Detection using a Handful of Gradient Steps
摘要：
分布外检测是普通神经网络长期以来一直无法实现的重要功能。深度神经网络（DNN）在输入显著超出分布（OOD）时倾向于生成过度自信的预测。当在野外使用机器学习系统时，这可能是危险的，因为检测攻击可能因此是困难的。最近的进展推断时间分布外检测有助于减轻这些问题中的一些。然而，现有的方法可能是限制性的，因为它们通常是计算昂贵的。此外，这些方法需要训练下游检测器模型，该模型学习从分布中检测OOD输入。因此，这增加了推理期间的延迟。在这里，我们提供了一个信息理论的角度来看，为什么神经网络本质上是无法OOD检测。我们试图通过使用少量的梯度下降步骤将训练模型转换为OOD检测器来减轻这些缺陷。我们的工作可以作为一种后处理方法，推理时间ML系统可以将训练模型转换为OOD检测器。在实验中，我们展示了我们的方法如何在流行的图像数据集上始终优于最先进的检测精度，同时还降低了计算复杂性。
英文摘要：
Out-of-distribution detection is an important capability that has long eluded vanilla neural networks. Deep Neural networks (DNNs) tend to generate over-confident predictions when presented with inputs that are significantly out-of-distribution (OOD). This can be dangerous when employing machine learning systems in the wild as detecting attacks can thus be difficult. Recent advances inference-time out-of-distribution detection help mitigate some of these problems. However, existing methods can be restrictive as they are often computationally expensive. Additionally, these methods require training of a downstream detector model which learns to detect OOD inputs from in-distribution ones. This, therefore, adds latency during inference. Here, we offer an information theoretic perspective on why neural networks are inherently incapable of OOD detection. We attempt to mitigate these flaws by converting a trained model into a an OOD detector using a handful of steps of gradient descent. Our work can be employed as a post-processing method whereby an inference-time ML system can convert a trained model into an OOD detector. Experimentally, we show how our method consistently outperforms the state-of-the-art in detection accuracy on popular image datasets while also reducing computational complexity.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
