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 OOD samples 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 outlier-class-aware logit calibration method is defined to enhance the long-tailed classification confidence. Extensive empirical results on three popular benchmarks CIFAR10-LT, CIFAR100-LT, 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.

翻译：现有分布外检测方法在平衡数据集上表现出色，但在长尾识别场景中效果不佳，具体表现为：1）分布外样本常被误分类为头部类别，和/或2）尾部类别样本被误判为分布外样本。针对这些问题，当前研究通常为辅助/伪分布外数据拟合一个先验分布，使其匹配长尾分布内数据。然而，由于无法获知真实分布外样本且长尾识别中存在严重的类别不平衡，难以获得准确的先验分布。避免使用此类先验的一个直接方案是学习一个异常类来囊括分布外样本。其核心挑战在于学习异常类时，需解决上述分布外样本与头部/尾部类别样本之间的混淆问题。为此，我们提出了一种新颖的校准异常类学习方法（COCL），其中：1）在异常类学习中引入去偏大间隔学习方法，以在表示空间中区分分布外样本与头部及尾部类别；2）定义了一种异常类感知的对数几率校准方法，以增强长尾分类的置信度。在CIFAR10-LT、CIFAR100-LT和ImageNet-LT三个主流基准上的大量实验结果表明，COCL在长尾识别中显著优于现有最优的分布外检测方法，同时能提升分布内数据分类准确率。代码已开源：https://github.com/mala-lab/COCL。