Long-tailed classification poses a challenge due to its heavy imbalance in class probabilities and tail-sensitivity risks with asymmetric misprediction costs. Recent attempts have used re-balancing loss and ensemble methods, but they are largely heuristic and depend heavily on empirical results, lacking theoretical explanation. Furthermore, existing methods overlook the decision loss, which characterizes different costs associated with tailed classes. This paper presents a general and principled framework from a Bayesian-decision-theory perspective, which unifies existing techniques including re-balancing and ensemble methods, and provides theoretical justifications for their effectiveness. From this perspective, we derive a novel objective based on the integrated risk and a Bayesian deep-ensemble approach to improve the accuracy of all classes, especially the "tail". Besides, our framework allows for task-adaptive decision loss which provides provably optimal decisions in varying task scenarios, along with the capability to quantify uncertainty. Finally, We conduct comprehensive experiments, including standard classification, tail-sensitive classification with a new False Head Rate metric, calibration, and ablation studies. Our framework significantly improves the current SOTA even on large-scale real-world datasets like ImageNet.

翻译：长尾分类因其类别概率的严重不均衡以及不对称误分类代价导致的尾灵敏度风险而面临挑战。近期方法尝试使用再平衡损失和集成方法，但这些方法大多基于启发式策略且严重依赖经验结果，缺乏理论解释。此外，现有方法忽略了描述尾部类别不同代价的决策损失。本文从贝叶斯决策理论视角提出一个通用且原则性的框架，该框架统一了包括再平衡和集成方法在内的现有技术，并为其有效性提供了理论依据。基于这一视角，我们推导出一个基于集成风险的新目标函数，并采用贝叶斯深度集成方法以提高所有类别（尤其是"尾部"类别）的准确率。此外，我们的框架支持任务自适应决策损失，可在不同任务场景下提供可证明的最优决策，并具备不确定性量化能力。最后，我们开展了全面实验，包括标准分类、基于新假头率度量的尾灵敏度分类、校准及消融研究。即使在ImageNet等大规模真实数据集上，我们的框架也显著超越了现有最优方法。