论文标题
使用以对象为中心的对手学习在视频中的局部异常检测
Local Anomaly Detection in Videos using Object-Centric Adversarial Learning
论文作者
论文摘要
我们基于一个以两个阶段为中心的对手框架提出了一种新颖的无监督方法，该方法仅需要对象区域来检测视频中的帧级局部异常。第一阶段包括学习当前外观与对象的过去梯度图像之间的对应关系，使我们可以从当前外观或反向产生过去的梯度。第二阶段以正常的对象行为提取了真实图像和生成的图像（外观和过去梯度）之间的部分重建错误，并以对抗性方式训练歧视器。在推理模式下，我们将经过训练的图像发生器与对抗学习的二进制分类器一起输出区域水平的异常检测分数。我们对四个公共基准测试，UMN，UCSD，Avenue和Shanghaitech进行了测试，与最先进的方法相比，我们提出的以对象为中心的对手方法可以产生竞争性甚至优越的结果。
We propose a novel unsupervised approach based on a two-stage object-centric adversarial framework that only needs object regions for detecting frame-level local anomalies in videos. The first stage consists in learning the correspondence between the current appearance and past gradient images of objects in scenes deemed normal, allowing us to either generate the past gradient from current appearance or the reverse. The second stage extracts the partial reconstruction errors between real and generated images (appearance and past gradient) with normal object behaviour, and trains a discriminator in an adversarial fashion. In inference mode, we employ the trained image generators with the adversarially learned binary classifier for outputting region-level anomaly detection scores. We tested our method on four public benchmarks, UMN, UCSD, Avenue and ShanghaiTech and our proposed object-centric adversarial approach yields competitive or even superior results compared to state-of-the-art methods.
