面向长尾识别的分布外检测：基于校准离群类学习的方法
Out-of-Distribution Detection in Long-Tailed Recognition with Calibrated Outlier Class Learning
AI总结：
针对长尾识别中OOD样本与头/尾类样本易混淆的问题，提出校准离群类学习方法COCL，通过去偏大间隔学习和离群类感知logit校准，同时提升OOD检测性能与分布内分类准确率。
摘要：
现有的分布外（OOD）检测方法在平衡数据集上表现优异，但在长尾识别（LTR）场景下效果显著下降，主要存在两类问题：1）OOD样本常被错误分类到头部类别；2）尾部类别的样本常被误判为OOD样本。为解决这些问题，现有研究尝试为长尾分布内（ID）数据拟合辅助/伪OOD数据的先验分布。然而，由于真实OOD样本的未知性以及LTR中严重的类别不平衡，很难获得准确的先验分布。避免依赖该先验的一种直接方案是学习一个离群类来封装所有OOD样本，但该方案的核心挑战是在学习离群类时，解决上述OOD样本与头部/尾部类样本之间的混淆问题。为此，本文提出了一种新颖的校准离群类学习（COCL）方法，该方法包含两个核心模块：1）在离群类学习中引入去偏大间隔学习方法，在表征空间中区分OOD样本与头部、尾部类样本；2）设计离群类感知的logit校准方法，提升长尾分类的置信度。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在长尾识别场景下的OOD检测性能显著优于当前最优方法，同时还能提升ID数据的分类准确率。代码已开源至https://github.com/mala-lab/COCL。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
