Detecting unusual input to neural networks
Evaluating a neural network on an input that differs markedly from the training data might cause erratic and flawed predictions. We study a method that judges the unusualness of an input by evaluating its informative content compared to the learned parameters. This technique can be used to judge whether a network is suitable for processing a certain input and to raise a red flag that unexpected behavior might lie ahead. We compare our approach to various methods for uncertainty evaluation from the literature for various datasets and scenarios. Specifically, we introduce a simple, effective method that allows to directly compare the output of such metrics for single input points even if these metrics live on different scales.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Detecting Unusual Input-Output Associations in Multivariate Conditional Data
Despite tremendous progress in outlier detection research in recent years, the majority of existing methods are designed only to detect unconditional outliers that correspond to unusual data patterns expressed in the joi…
Outlier DetectionSet Features for Anomaly Detection
This paper proposes to use set features for detecting anomalies in samples that consist of unusual combinations of normal elements. Many leading methods discover anomalies by detecting an unusual part of a sample. For ex…
Anomaly DetectionDensity EstimationTime SeriesTime Series Anomaly DetectionConditional anomaly detection methods for patient-management alert systems
Anomaly detection methods can be very useful in identifying unusual or interesting patterns in data. A recently proposed conditional anomaly detection framework extends anomaly detection to the problem of identifying ano…
Anomaly DetectionMetric LearningConditional anomaly detection with soft harmonic functions
In this paper, we consider the problem of conditional anomaly detection that aims to identify data instances with an unusual response or a class label. We develop a new non-parametric approach for conditional anomaly det…
Anomaly DetectionEfficacy of Pixel-Level OOD Detection for Semantic Segmentation
The detection of out of distribution samples for image classification has been widely researched. Safety critical applications, such as autonomous driving, would benefit from the ability to localise the unusual objects c…
Autonomous DrivingGeneral Classificationimage-classificationImage Classification+2