Detecting Anomalous Faces with 'No Peeking' Autoencoders
Detecting anomalous faces has important applications. For example, a system might tell when a train driver is incapacitated by a medical event, and assist in adopting a safe recovery strategy. These applications are demanding, because they require accurate detection of rare anomalies that may be seen only at runtime. Such a setting causes supervised methods to perform poorly. We describe a method for detecting an anomalous face image that meets these requirements. We construct a feature vector that reliably has large entries for anomalous images, then use various simple unsupervised methods to score the image based on the feature. Obvious constructions (autoencoder codes; autoencoder residuals) are defeated by a 'peeking' behavior in autoencoders. Our feature construction removes rectangular patches from the image, predicts the likely content of the patch conditioned on the rest of the image using a specially trained autoencoder, then compares the result to the image. High scores suggest that the patch was difficult for an autoencoder to predict, and so is likely anomalous. We demonstrate that our method can identify real anomalous face images in pools of typical images, taken from celeb-A, that is much larger than usual in state-of-the-art experiments. A control experiment based on our method with another set of normal celebrity images - a 'typical set', but nonceleb-A are not identified as anomalous; confirms this is not due to special properties of celeb-A.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Automatically detecting anomalous exoplanet transits
Raw light curve data from exoplanet transits is too complex to naively apply traditional outlier detection methods. We propose an architecture which estimates a latent representation of both the main transit and residual…
Outlier DetectionLabel-free Anomaly Detection in Aerial Agricultural Images with Masked Image Modeling
Detecting various types of stresses (nutritional, water, nitrogen, etc.) in agricultural fields is critical for farmers to ensure maximum productivity. However, stresses show up in different shapes and sizes across diffe…
Anomaly DetectionSelf-Supervised LearningDetecting Compromised IoT Devices Using Autoencoders with Sequential Hypothesis Testing
IoT devices fundamentally lack built-in security mechanisms to protect themselves from security attacks. Existing works on improving IoT security mostly focus on detecting anomalous behaviors of IoT devices. However, the…
Anomaly DetectionEnhancing anomaly detection with topology-aware autoencoders
Anomaly detection in high-energy physics is essential for identifying new physics beyond the Standard Model. Autoencoders provide a signal-agnostic approach but are limited by the topology of their latent space. This wor…
Anomaly Detectionp-value peeking and estimating extrema
A pervasive issue in statistical hypothesis testing is that the reported $p$-values are biased downward by data "peeking" -- the practice of reporting only progressively extreme values of the test statistic as more data …
Two-sample testing