Unsupervised anomaly localization using VAE and beta-VAE
Variational Auto-Encoders (VAEs) have shown great potential in the unsupervised learning of data distributions. An VAE trained on normal images is expected to only be able to reconstruct normal images, allowing the localization of anomalous pixels in an image via manipulating information within the VAE ELBO loss. The ELBO consists of KL divergence loss (image-wise) and reconstruction loss (pixel-wise). It is natural and straightforward to use the later as the predictor. However, usually local anomaly added to a normal image can deteriorate the whole reconstructed image, causing segmentation using only naive pixel errors not accurate. Energy based projection was proposed to increase the reconstruction accuracy of normal regions/pixels, which achieved the state-of-the-art localization accuracy on simple natural images. Another possible predictors are ELBO and its components gradients with respect to each pixels. Previous work claimed that KL gradient is a robust predictor. In this paper, we argue that the energy based projection in medical imaging is not as useful as on natural images. Moreover, we observe that the robustness of KL gradient predictor totally depends on the setting of the VAE and dataset. We also explored the effect of the weight of KL loss within beta-VAE and predictor ensemble in anomaly localization.
Code (0)
등록된 구현이 없습니다.
Tasks
Anomaly LocalizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Post-Hoc Calibrated Anomaly Detection
Deep unsupervised anomaly detection has seen improvements in a supervised binary classification paradigm in which auxiliary external data is included in the training set as anomalous data in a process referred to as outl…
Anomaly DetectionBinary ClassificationUnsupervised Anomaly DetectionAnomaly Detection Based on Unsupervised Disentangled Representation Learning in Combination with Manifold Learning
Identifying anomalous samples from highly complex and unstructured data is a crucial but challenging task in a variety of intelligent systems. In this paper, we present a novel deep anomaly detection framework named AnoD…
Anomaly DetectionDensity EstimationDisentanglementRepresentation Learning+2OmniAL: A Unified CNN Framework for Unsupervised Anomaly Localization
Unsupervised anomaly localization and detection is crucial for industrial manufacturing processes due to the lack of anomalous samples. Recent unsupervised advances on industrial anomaly detection achieve high perfor…
Anomaly DetectionAnomaly LocalizationMulti-class Anomaly DetectionCoincident Learning for Unsupervised Anomaly Detection
Anomaly detection is an important task for complex systems (e.g., industrial facilities, manufacturing, large-scale science experiments), where failures in a sub-system can lead to low yield, faulty products, or even dam…
Anomaly DetectionTime SeriesTime Series AnalysisUnsupervised Anomaly DetectionLogicAL: Towards logical anomaly synthesis for unsupervised anomaly localization
Anomaly localization is a practical technology for improving industrial production line efficiency. Due to anomalies are manifold and hard to be collected, existing unsupervised researches are usually equipped with anoma…
Anomaly Localization