Deep neural networks are known to be vulnerable to unseen data: they may wrongly assign high confidence stcores to out-distribuion samples. Recent works try to solve the problem using representation learning methods and specific metrics. In this paper, we propose a simple, yet effective post-hoc anomaly detection algorithm named Test Time Augmentation Anomaly Detection (TTA-AD), inspired by a novel observation. Specifically, we observe that in-distribution data enjoy more consistent predictions for its original and augmented versions on a trained network than out-distribution data, which separates in-distribution and out-distribution samples. Experiments on various high-resolution image benchmark datasets demonstrate that TTA-AD achieves comparable or better detection performance under dataset-vs-dataset anomaly detection settings with a 60%~90\% running time reduction of existing classifier-based algorithms. We provide empirical verification that the key to TTA-AD lies in the remaining classes between augmented features, which has long been partially ignored by previous works. Additionally, we use RUNS as a surrogate to analyze our algorithm theoretically.
翻译:据知深神经网络容易受不可见的数据的影响:它们可能错误地将高度自信的分流点分配给分流样本;最近的工作试图利用代表性学习方法和特定度量来解决问题。在本文中,我们提出了一个简单而有效的超常检测算法,名为TTA-AD(TTA-AD),受新观察的启发,名为TTA-AD(TTA-AD) 。具体地说,我们观察到,在经过培训的网络上,在原始和扩充版本方面,分配数据比在分布和分流样本中分离的分流数据得到更加一致的预测。关于各种高分辨率图像基准数据集的实验表明,TTA-AD在数据集异常检测设置下取得了可比的或更好的检测性能,正在减少现有的基于分类法的算法(TA-AD)的时间。我们提供经验性核查,TA-A-AD的关键存在于增强的特性之间的剩余类别,而以前曾部分被忽略过。此外,我们使用RUNS(RUNS)作为分析我们理论算法的替代。