arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.14945cs.CV
收藏

基于原型引导的鉴别潜在嵌入的异常检测

Anomaly Detection with Prototype-Guided Discriminative Latent Embeddings

Peng Cheng Laboratory(鹏城实验室)

Yuandu Lai, Yahong Han, Yaowei Wang

摘要:

最近对视频异常检测(VAD)的努力试图学习一个深度自动编码器来描述具有小重建错误的正常事件模式。具有大的重建误差的视频输入在测试时被视为异常。然而,由于深度自编码器强大的泛化能力,这些方法有时会很好地重建异常输入。为了解决这个问题,我们提出了一种新的异常检测方法,它利用正常数据的判别原型来重建视频帧。这样,该模型将有利于正常事件的重建,而扭曲异常事件的重建。具体来说,我们使用一个原型引导的内存模块来执行歧视性的潜在嵌入。我们引入了一个新的记忆模块的判别准则,以及相应的损失函数,它可以鼓励记忆项记录正常数据的代表性嵌入,即原型。此外,我们设计了一种新颖的双分支自动编码器,它由未来帧预测网络和RGB差分生成网络组成,它们共享同一个编码器。堆叠的RGB差异包含运动信息,就像光流一样,因此我们的模型可以学习时间规律。我们评估了我们的方法在三个基准数据集上的有效性,实验结果表明,所提出的方法优于最先进的。

英文摘要:

Recent efforts towards video anomaly detection (VAD) try to learn a deep autoencoder to describe normal event patterns with small reconstruction errors. The video inputs with large reconstruction errors are regarded as anomalies at the test time. However, these methods sometimes reconstruct abnormal inputs well because of the powerful generalization ability of deep autoencoder. To address this problem, we present a novel approach for anomaly detection, which utilizes discriminative prototypes of normal data to reconstruct video frames. In this way, the model will favor the reconstruction of normal events and distort the reconstruction of abnormal events. Specifically, we use a prototype-guided memory module to perform discriminative latent embedding. We introduce a new discriminative criterion for the memory module, as well as a loss function correspondingly, which can encourage memory items to record the representative embeddings of normal data, i.e. prototypes. Besides, we design a novel two-branch autoencoder, which is composed of a future frame prediction network and an RGB difference generation network that share the same encoder. The stacked RGB difference contains motion information just like optical flow, so our model can learn temporal regularity. We evaluate the effectiveness of our method on three benchmark datasets and experimental results demonstrate the proposed method outperforms the state-of-the-art.

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。

↑