Current unsupervised anomaly localization approaches rely on generative models to learn the distribution of normal images, which is later used to identify potential anomalous regions derived from errors on the reconstructed images. However, a main limitation of nearly all prior literature is the need of employing anomalous images to set a class-specific threshold to locate the anomalies. This limits their usability in realistic scenarios, where only normal data is typically accessible. Despite this major drawback, only a handful of works have addressed this limitation, by integrating supervision on attention maps during training. In this work, we propose a novel formulation that does not require accessing images with abnormalities to define the threshold. Furthermore, and in contrast to very recent work, the proposed constraint is formulated in a more principled manner, leveraging well-known knowledge in constrained optimization. In particular, the equality constraint on the attention maps in prior work is replaced by an inequality constraint, which allows more flexibility. In addition, to address the limitations of penalty-based functions we employ an extension of the popular log-barrier methods to handle the constraint. Last, we propose an alternative regularization term that maximizes the Shannon entropy of the attention maps, reducing the amount of hyperparameters of the proposed model. Comprehensive experiments on two publicly available datasets on brain lesion segmentation demonstrate that the proposed approach substantially outperforms relevant literature, establishing new state-of-the-art results for unsupervised lesion segmentation, and without the need to access anomalous images.
翻译:目前未经监督的异常本地化方法依靠基因模型来了解正常图像的分布,而通常图像的分布后来被用于确定因重建图像错误而可能产生的异常区域。然而,几乎所有先前文献的主要局限性是,需要使用异常图像来设定一个特定等级的阈值,以定位异常点。这限制了其在现实情景中的可用性,在现实情景中,只有正常数据通常可以获得。尽管存在这一重大缺陷,但只有少数作品通过在培训中整合对关注地图的监督,解决了这一局限性。在这项工作中,我们提议了一种新颖的提法,不需要以异常图像访问来界定阈值。此外,与最近的工作相反,拟议的限制是以更有原则的方式拟订的,利用众所周知的知识来定位异常的阈值来确定异常区域。特别是,以前工作中对关注地图的平等性制约被一种不平等性制约所取代,而这种不平等性制约通常只有正常数据。此外,为了解决基于惩罚的功能的局限性,我们使用了一种受欢迎的日志障碍方法来应对制约。最后,我们提议采用另一种正规化术语,即不要求以异常方式访问图像来界定阈值。此外,与最近的工作不同的做法是,以更加有原则的方式,以更符合原则的方式来利用众所周知的方式,在综合地图上的拟议结构部分中,需要尽可能地展示中,从而大量地展示相关的结果,从而在公开地展示。