Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

2-2024

Abstract

Existing out-of-distribution (OOD) methods have shown great success on balanced datasets but become ineffective in long-tailed recognition (LTR) scenarios where 1) OOD samples are often wrongly classified into head classes and/or 2) tail-class samples are treated as OOD samples. To address these issues, current studies fit a prior distribution of auxiliary/pseudo OOD data to the long-tailed in-distribution (ID) data. However, it is difficult to obtain such an accurate prior distribution given the unknowingness of real OOD samples and heavy class imbalance in LTR. A straightforward solution to avoid the requirement of this prior is to learn an outlier class to encapsulate the OOD samples. The main challenge is then to tackle the aforementioned confusion between OODsamples and head/tail-class samples when learning the outlier class. To this end, we introduce a novel calibrated outlier class learning (COCL) approach, in which 1) a debiased large margin learning method is introduced in the outlier class learning to distinguish OOD samples from both head and tail classes in the representation space and 2) an outlierclass-aware logit calibration method is defined to enhance the long-tailed classification confidence. Extensive empirical results on three popular benchmarks CIFAR10-LT, CIFAR100LT, and ImageNet-LT demonstrate that COCL substantially outperforms state-of-the-art OOD detection methods in LTR while being able to improve the classification accuracy on ID data. Code is available at https://github.com/mala-lab/COCL.

Keywords

Object Detection & Categorization, Adversarial Attacks & Robustness, Applications

Discipline

Artificial Intelligence and Robotics | Graphics and Human Computer Interfaces

Research Areas

Intelligent Systems and Optimization

Areas of Excellence

Digital transformation

Publication

Proceedings of the 38th AAAI Conference on Artificial Intelligence, AAAI 2024, Vancouver, Canada, February 20-27

Volume

38

First Page

4216

Last Page

4224

ISBN

9781577358879

Identifier

10.1609/AAAI.V38I5.28217

Publisher

AAAI Press

City or Country

Vancouver

Additional URL

https://doi.org/10.1609/aaai.v38i5.28217

Download

Share

COinS