Elsa: Energy-based learning for semi-supervised anomaly detection
Anomaly detection aims at identifying deviant instances from the normal data distribution. Many advances have been made in the field, including the innovative use of unsupervised contrastive learning. However, existing methods generally assume clean training data and are limited when the data contain unknown anomalies. This paper presents Elsa, a novel semi-supervised anomaly detection approach that unifies the concept of energy-based models with unsupervised contrastive learning. Elsa instills robustness against any data contamination by a carefully designed fine-tuning step based on the new energy function that forces the normal data to be divided into classes of prototypes. Experiments on multiple contamination scenarios show the proposed model achieves SOTA performance. Extensive analyses also verify the contribution of each component in the proposed model. Beyond the experiments, we also offer a theoretical interpretation of why contrastive learning alone cannot detect anomalies under data contamination.
Code (0)
등록된 구현이 없습니다.
Tasks
Anomaly DetectionContrastive LearningSemi-supervised Anomaly DetectionSupervised Anomaly DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
PAC-Wrap: Semi-Supervised PAC Anomaly Detection
Anomaly detection is essential for preventing hazardous outcomes for safety-critical applications like autonomous driving. Given their safety-criticality, these applications benefit from provable bounds on various errors…
Anomaly DetectionAutonomous DrivingUnsupervised Anomaly DetectionAutoencoders for unsupervised anomaly detection in high energy physics
Autoencoders are widely used in machine learning applications, in particular for anomaly detection. Hence, they have been introduced in high energy physics as a promising tool for model-independent new physics searches. …
Anomaly DetectionJet TaggingTAGUnsupervised Anomaly Detection+1Understanding Bias in Anomaly Detection: A Semi-Supervised View with PAC Guarantees
Anomaly detection presents a unique challenge in machine learning, due to the scarcity of labeled anomaly data. Existing work attempts to mitigate such problems via semi-supervised learning, i.e., augmenting unsupervised…
Anomaly DetectionSemi-supervised Anomaly DetectionSupervised Anomaly DetectionUnsupervised Anomaly DetectionAGAD: Adversarial Generative Anomaly Detection
Anomaly detection suffered from the lack of anomalies due to the diversity of abnormalities and the difficulties of obtaining large-scale anomaly data. Semi-supervised anomaly detection methods are often used to solely l…
Anomaly DetectionDiversitySemi-supervised Anomaly DetectionSupervised Anomaly DetectionELSA: A Throughput-Optimized Design of an LSTM Accelerator for Energy-Constrained Devices
The next significant step in the evolution and proliferation of artificial intelligence technology will be the integration of neural network (NN) models within embedded and mobile systems. This calls for the design of co…
Language ModelingLanguage Modelling