arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2203.01671eess.IVcs.CV
收藏

约束无监督异常分割

Constrained unsupervised anomaly segmentation

Universitat Politècnica de València(瓦伦西亚理工大学);École de Technologie Supérieure(高等技术学院)

Julio Silva-Rodríguez, Valery Naranjo, Jose Dolz

摘要:

目前的无监督异常定位方法依赖于生成模型来学习正常图像的分布,该分布随后用于识别由重建图像上的错误导出的潜在异常区域。然而,几乎所有现有文献的主要限制是需要采用异常图像来设置特定于类别的阈值来定位异常。这限制了它们在现实场景中的可用性,在现实场景中通常只能访问正常数据。尽管有这个主要的缺点,只有少数的作品已经解决了这个限制,通过在训练过程中整合注意力地图的监督。在这项工作中,我们提出了一种新的配方,不需要访问异常的图像来定义阈值。此外,与最近的工作相比,所提出的约束以更有原则的方式制定,利用约束优化中的众所周知的知识。特别是,在以前的工作中的注意力地图的等式约束被替换为不等式约束,这允许更多的灵活性。此外,为了解决基于惩罚函数的限制,我们采用了流行的日志屏障方法来处理约束的扩展。最后,我们提出了一个替代的正则化项,最大化注意力地图的香农熵,减少了所提出的模型的超参数的数量。在两个公开的脑病变分割数据集上进行的综合实验表明,所提出的方法大大优于相关文献,为无监督病变分割建立了新的最先进的结果,并且不需要访问异常图像。

英文摘要:

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.

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。

↑