A Deep Generative Distance-Based Classifier for Out-of-Domain Detection with Mahalanobis Space
Detecting out-of-domain (OOD) input intents is critical in the task-oriented dialog system. Different from most existing methods that rely heavily on manually labeled OOD samples, we focus on the unsupervised OOD detection scenario where there are no labeled OOD samples except for labeled in-domain data. In this paper, we propose a simple but strong generative distance-based classifier to detect OOD samples. We estimate the class-conditional distribution on feature spaces of DNNs via Gaussian discriminant analysis (GDA) to avoid over-confidence problems. And we use two distance functions, Euclidean and Mahalanobis distances, to measure the confidence score of whether a test sample belongs to OOD. Experiments on four benchmark datasets show that our method can consistently outperform the baselines.
Code (0)
등록된 구현이 없습니다.
Tasks
Out of Distribution (OOD) DetectionSimilar Papers 제목 키워드 기반
Why is the Mahalanobis Distance Effective for Anomaly Detection?
The Mahalanobis distance-based confidence score, a recently proposed anomaly detection method for pre-trained neural classifiers, achieves state-of-the-art performance on both out-of-distribution (OoD) and adversarial ex…
Anomaly DetectionGeneral ClassificationMetric LearningOut of Distribution (OOD) DetectionClassification Using Global and Local Mahalanobis Distances
We propose a novel semiparametric classifier based on Mahalanobis distances of an observation from the competing classes. Our tool is a generalized additive model with the logistic link function that uses these distances…
ClassificationE-ADDA: Unsupervised Adversarial Domain Adaptation Enhanced by a New Mahalanobis Distance Loss for Smart Computing
In smart computing, the labels of training samples for a specific task are not always abundant. However, the labels of samples in a relevant but different dataset are available. As a result, researchers have relied on un…
Domain AdaptationOut-of-Distribution DetectionUnsupervised Domain AdaptationGenerative Max-Mahalanobis Classifiers for Image Classification, Generation and More
Joint Energy-based Model (JEM) of Grathwohl et al. shows that a standard softmax classifier can be reinterpreted as an energy-based model (EBM) for the joint distribution p(x,y); the resulting model can be optimized to i…
Adversarial RobustnessClassificationGeneral Classificationimage-classification+3On the use of Mahalanobis distance for out-of-distribution detection with neural networks for medical imaging
Implementing neural networks for clinical use in medical applications necessitates the ability for the network to detect when input data differs significantly from the training data, with the aim of preventing unreliable…
Out-of-Distribution DetectionOut of Distribution (OOD) Detection