One-class novelty detection is conducted to identify anomalous instances, with different distributions from the expected normal instances. In this paper, the Generative Adversarial Network based on the Encoder-Decoder-Encoder scheme (EDE-GAN) achieves state-of-the-art performance. The two factors bellow serve the above purpose: 1) The EDE-GAN calculates the distance between two latent vectors as the anomaly score, which is unlike the previous methods by utilizing the reconstruction error between images. 2) The model obtains best results when the batch size is set to 1. To illustrate their superiority, we design a new GAN architecture, and compare performances according to different batch sizes. Moreover, with experimentation leads to discovery, our result implies there is also evidence of just how beneficial constraint on the latent space are when engaging in model training. In an attempt to learn compact and fast models, we present a new technology, Progressive Knowledge Distillation with GANs (P-KDGAN), which connects two standard GANs through the designed distillation loss. Two-step progressive learning continuously augments the performance of student GANs with improved results over single-step approach. Our experimental results on CIFAR-10, MNIST, and FMNIST datasets illustrate that P-KDGAN improves the performance of the student GAN by 2.44%, 1.77%, and 1.73% when compressing the computationat ratios of 24.45:1, 311.11:1, and 700:1, respectively.

翻译：单类新颖性检测旨在识别与预期正常实例分布不同的异常实例。本文提出基于编码器-解码器-编码器架构的生成对抗网络（EDE-GAN）取得了最优性能。以下两个因素支撑了上述目标：1）EDE-GAN计算两个潜在向量之间的距离作为异常分数，这与以往利用图像间重构误差的方法不同；2）当批量大小设为1时，模型获得最佳结果。为阐明其优越性，我们设计了一种新的GAN架构，并根据不同批量大小进行了性能对比。此外，实验探索发现，我们的结果表明在模型训练中施加潜在空间约束具有显著益处。为学习紧凑且快速的模型，我们提出了一项新技术——渐进式知识蒸馏生成对抗网络（P-KDGAN），通过设计的蒸馏损失连接两个标准GAN。两步渐进式学习持续增强学生GAN的性能，相较于单步方法取得了更优结果。在CIFAR-10、MNIST和FMNIST数据集上的实验表明，当计算压缩比分别为24.45:1、311.11:1和700:1时，P-KDGAN将学生GAN的性能分别提升了2.44%、1.77%和1.73%。