Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation
Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation
复制标题
DOI：
10.1007/978-3-030-58452-8_9
复制
发表时间：
2020-03
期刊：
影响因子：
--
通讯作者：
Yingda Xia;Yi Zhang;Fengze Liu;Wei Shen;A. Yuille
中科院分区：
文献类型：
--
作者：
Yingda Xia;Yi Zhang;Fengze Liu;Wei Shen;A. Yuille
检测故障和异常的能力是为计算机视觉应用构建可靠系统的基本要求，特别是语义分割的安全关键型应用，如自动驾驶和医学图像分析。在本文中，我们系统地研究了故障和异常检测的语义分割，并提出了一个统一的框架，由两个模块，以解决这两个相关的问题。第一模块是图像合成模块，其从分割布局图生成合成图像，并且第二模块是比较模块，其计算合成图像与输入图像之间的差异。我们在三个具有挑战性的数据集上验证了我们的框架，并大幅提高了最先进的水平，即，Cityscapes的AUPR错误率为6%，MSD中胰腺肿瘤分割的Pearson相关性为7%，StreetHazards异常分割的AUPR为20%。
The ability to detect failures and anomalies are fundamental requirements for building reliable systems for computer vision applications, especially safety-critical applications of semantic segmentation, such as autonomous driving and medical image analysis. In this paper, we systematically study failure and anomaly detection for semantic segmentation and propose a unified framework, consisting of two modules, to address these two related problems. The first module is an image synthesis module, which generates a synthesized image from a segmentation layout map, and the second is a comparison module, which computes the difference between the synthesized image and the input image. We validate our framework on three challenging datasets and improve the state-of-the-arts by large margins,i.e., 6% AUPR-Error on Cityscapes, 7% Pearson correlation on pancreatic tumor segmentation in MSD and 20% AUPR on StreetHazards anomaly segmentation.