paper-with-me

홈 › Papers

A Deep Generative Distance-Based Classifier for Out-of-Domain Detection with Mahalanobis Space

2020-12-01 · COLING 2020 8 · Hong Xu, Keqing He, Yuanmeng Yan, Sihong Liu, Zijun Liu, Weiran Xu

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.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Out of Distribution (OOD) Detection

Similar Papers 제목 키워드 기반

Why is the Mahalanobis Distance Effective for Anomaly Detection?

2020-03-01 · Ryo Kamoi, Kei Kobayashi

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) Detection

Classification Using Global and Local Mahalanobis Distances

2024-02-13 · Annesha Ghosh, Anil K. Ghosh, Rita SahaRay, Soham Sarkar

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…

Classification

E-ADDA: Unsupervised Adversarial Domain Adaptation Enhanced by a New Mahalanobis Distance Loss for Smart Computing

2022-01-24 · Ye Gao, Brian Baucom, Karen Rose, Kristina Gordon 외

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 Adaptation

Generative Max-Mahalanobis Classifiers for Image Classification, Generation and More

2021-01-01 · Xiulong Yang, Hui Ye, Yang Ye, Xiang Li 외

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+3

On the use of Mahalanobis distance for out-of-distribution detection with neural networks for medical imaging

2023-09-04 · Harry Anthony, Konstantinos Kamnitsas

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