Class-wise Thresholding for Detecting Out-of-Distribution Data

10/28/2021
by   Matteo Guarrera, et al.
11

We consider the problem of detecting OoD(Out-of-Distribution) input data when using deep neural networks, and we propose a simple yet effective way to improve the robustness of several popular OoD detection methods against label shift. Our work is motivated by the observation that most existing OoD detection algorithms consider all training/test data as a whole, regardless of which class entry each input activates (inter-class differences). Through extensive experimentation, we have found that such practice leads to a detector whose performance is sensitive and vulnerable to label shift. To address this issue, we propose a class-wise thresholding scheme that can apply to most existing OoD detection algorithms and can maintain similar OoD detection performance even in the presence of label shift in the test distribution.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/10/2020

Robust Classification under Class-Dependent Domain Shift

Investigation of machine learning algorithms robust to changes between t...
research
09/18/2020

Sequential changepoint detection for label shift in classification

Classifier predictions often rely on the assumption that new observation...
research
08/20/2018

Out-of-Distribution Detection using Multiple Semantic Label Representations

Deep Neural Networks are powerful models that attained remarkable result...
research
11/17/2022

Online Distribution Shift Detection via Recency Prediction

When deploying modern machine learning-enabled robotic systems in high-s...
research
03/27/2023

Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency

Deep neural networks are proven to be vulnerable to backdoor attacks. De...
research
05/17/2022

A unified framework for dataset shift diagnostics

Most machine learning (ML) methods assume that the data used in the trai...
research
02/26/2020

Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data

Deep neural networks have attained remarkable performance when applied t...

Please sign up or login with your details

Forgot password? Click here to reset