Deep One-Class Classification via Interpolated Gaussian Descriptor

25 Jan 2021  ·  Yuanhong Chen, Yu Tian, Guansong Pang, Gustavo Carneiro ·

One-class classification (OCC) aims to learn an effective data description to enclose all normal training samples and detect anomalies based on the deviation from the data description. Current state-of-the-art OCC models learn a compact normality description by hyper-sphere minimisation, but they often suffer from overfitting the training data, especially when the training set is small or contaminated with anomalous samples. To address this issue, we introduce the interpolated Gaussian descriptor (IGD) method, a novel OCC model that learns a one-class Gaussian anomaly classifier trained with adversarially interpolated training samples. The Gaussian anomaly classifier differentiates the training samples based on their distance to the Gaussian centre and the standard deviation of these distances, offering the model a discriminability w.r.t. the given samples during training. The adversarial interpolation is enforced to consistently learn a smooth Gaussian descriptor, even when the training data is small or contaminated with anomalous samples. This enables our model to learn the data description based on the representative normal samples rather than fringe or anomalous samples, resulting in significantly improved normality description. In extensive experiments on diverse popular benchmarks, including MNIST, Fashion MNIST, CIFAR10, MVTec AD and two medical datasets, IGD achieves better detection accuracy than current state-of-the-art models. IGD also shows better robustness in problems with small or contaminated training sets. Code is available at

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Anomaly Detection CIFAR-10 IGD ROC AUC 91.25 # 1
Anomaly Detection Fashion-MNIST IGD ROC AUC 94.4 # 3
Anomaly Detection MVTec AD IGD Detection AUROC 93.4 # 23
Segmentation AUROC 93.0 # 23
Anomaly Detection One-class CIFAR-10 IGD AUROC 91.3 # 9


No methods listed for this paper. Add relevant methods here