论文标题
用于异常检测和特征学习的近端敏感误差
Proximally Sensitive Error for Anomaly Detection and Feature Learning
论文作者
论文摘要
平均平方误差（MSE）是多维实体（包括图像）之间表达差异最广泛的指标之一。但是，MSE并不是局部敏感的，因为它没有考虑（像素）差异的空间排列，这对于图像等结构化数据类型很重要。这种空间安排带有有关差异来源的信息；因此，一个错误的函数也包含错误的位置可能会导致更有意义的距离度量。我们引入了近端敏感的误差（PSE），我们建议误差度量中的区域重点可以“突出显示”图像与句法/随机偏差之间的语义差异。我们证明，可以利用这种重点来进行异常/遮挡检测任务。我们进一步探讨了它作为损失函数的实用性，以帮助模型专注于语义对象的学习表示，而不是最大程度地减少句法重建噪声。
Mean squared error (MSE) is one of the most widely used metrics to expression differences between multi-dimensional entities, including images. However, MSE is not locally sensitive as it does not take into account the spatial arrangement of the (pixel) differences, which matters for structured data types like images. Such spatial arrangements carry information about the source of the differences; therefore, an error function that also incorporates the location of errors can lead to a more meaningful distance measure. We introduce Proximally Sensitive Error (PSE), through which we suggest that a regional emphasis in the error measure can 'highlight' semantic differences between images over syntactic/random deviations. We demonstrate that this emphasis can be leveraged upon for the task of anomaly/occlusion detection. We further explore its utility as a loss function to help a model focus on learning representations of semantic objects instead of minimizing syntactic reconstruction noise.
