Multi-Class Data Description for Out-of-distribution Detection

04/02/2021
by   Dongha Lee, et al.
0

The capability of reliably detecting out-of-distribution samples is one of the key factors in deploying a good classifier, as the test distribution always does not match with the training distribution in most real-world applications. In this work, we present a deep multi-class data description, termed as Deep-MCDD, which is effective to detect out-of-distribution (OOD) samples as well as classify in-distribution (ID) samples. Unlike the softmax classifier that only focuses on the linear decision boundary partitioning its latent space into multiple regions, our Deep-MCDD aims to find a spherical decision boundary for each class which determines whether a test sample belongs to the class or not. By integrating the concept of Gaussian discriminant analysis into deep neural networks, we propose a deep learning objective to learn class-conditional distributions that are explicitly modeled as separable Gaussian distributions. Thereby, we can define the confidence score by the distance of a test sample from each class-conditional distribution, and utilize it for identifying OOD samples. Our empirical evaluation on multi-class tabular and image datasets demonstrates that Deep-MCDD achieves the best performances in distinguishing OOD samples while showing the classification accuracy as high as the other competitors.

READ FULL TEXT

page 7

page 9

research
07/10/2018

A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks

Detecting test samples drawn sufficiently far away from the training dis...
research
11/23/2022

Reconnoitering the class distinguishing abilities of the features, to know them better

The relevance of machine learning (ML) in our daily lives is closely int...
research
12/22/2021

GAN Based Boundary Aware Classifier for Detecting Out-of-distribution Samples

This paper focuses on the problem of detecting out-of-distribution (ood)...
research
11/07/2022

Interpreting deep learning output for out-of-distribution detection

Commonly used AI networks are very self-confident in their predictions, ...
research
11/02/2021

Out of distribution detection for skin and malaria images

Deep neural networks have shown promising results in disease detection a...
research
08/20/2021

Does Adversarial Oversampling Help us?

Traditional oversampling methods are generally employed to handle class ...
research
05/28/2018

Confidence Prediction for Lexicon-Free OCR

Having a reliable accuracy score is crucial for real world applications ...

Please sign up or login with your details

Forgot password? Click here to reset