Out-of-distribution Detection with Implicit Outlier Transformation

03/09/2023
by   Qizhou Wang, et al.
0

Outlier exposure (OE) is powerful in out-of-distribution (OOD) detection, enhancing detection capability via model fine-tuning with surrogate OOD data. However, surrogate data typically deviate from test OOD data. Thus, the performance of OE, when facing unseen OOD data, can be weakened. To address this issue, we propose a novel OE-based approach that makes the model perform well for unseen OOD situations, even for unseen OOD cases. It leads to a min-max learning scheme – searching to synthesize OOD data that leads to worst judgments and learning from such OOD data for uniform performance in OOD detection. In our realization, these worst OOD data are synthesized by transforming original surrogate ones. Specifically, the associated transform functions are learned implicitly based on our novel insight that model perturbation leads to data transformation. Our methodology offers an efficient way of synthesizing OOD data, which can further benefit the detection model, besides the surrogate OOD data. We conduct extensive experiments under various OOD detection setups, demonstrating the effectiveness of our method against its advanced counterparts.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/20/2022

Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantities

It is an important problem in trustworthy machine learning to recognize ...
research
06/07/2021

Fine-grained Out-of-Distribution Detection with Mixup Outlier Exposure

Enabling out-of-distribution (OOD) detection for DNNs is critical for th...
research
10/24/2022

Are we really making much progress in unsupervised graph outlier detection? Revisiting the problem with new insight and superior method

A large number of studies on Graph Outlier Detection (GOD) have emerged ...
research
08/02/2023

Three Factors to Improve Out-of-Distribution Detection

In the problem of out-of-distribution (OOD) detection, the usage of auxi...
research
05/11/2017

Incremental Learning Through Deep Adaptation

Given an existing trained neural network, it is often desirable to be ab...
research
10/12/2020

Unseen Target Stance Detection with Adversarial Domain Generalization

Although stance detection has made great progress in the past few years,...

Please sign up or login with your details

Forgot password? Click here to reset