The problem of deep long-tailed learning, a prevalent challenge in the realm of generic visual recognition, persists in a multitude of real-world applications. To tackle the heavily-skewed dataset issue in long-tailed classification, prior efforts have sought to augment existing deep models with the elaborate class-balancing strategies, such as class rebalancing, data augmentation, and module improvement. Despite the encouraging performance, the limited class knowledge of the tailed classes in the training dataset still bottlenecks the performance of the existing deep models. In this paper, we propose an innovative long-tailed learning paradigm that breaks the bottleneck by guiding the learning of deep networks with external prior knowledge. This is specifically achieved by devising an elaborated ``prophetic'' teacher, termed as ``Propheter'', that aims to learn the potential class distributions. The target long-tailed prediction model is then optimized under the instruction of the well-trained ``Propheter'', such that the distributions of different classes are as distinguishable as possible from each other. Experiments on eight long-tailed benchmarks across three architectures demonstrate that the proposed prophetic paradigm acts as a promising solution to the challenge of limited class knowledge in long-tailed datasets. The developed code is publicly available at \url{https://github.com/tcmyxc/propheter}.

翻译：深度长尾学习问题作为通用视觉识别领域中的普遍挑战，持续存在于众多实际应用中。为应对长尾分类中数据集严重偏斜的问题，先前的研究致力于通过精心的类别平衡策略（如类别重平衡、数据增强和模块改进）来增强现有深度模型。尽管取得了令人鼓舞的性能，但训练数据集中尾部类别知识的局限性仍制约着现有深度模型的性能。本文提出一种创新的长尾学习范式，通过引入外部先验知识指导深度网络学习来突破这一瓶颈。具体而言，我们设计了一种精巧的"先知式"教师（称为"Propheter"），旨在学习潜在类别分布。随后，在训练有素的"Propheter"指导下优化目标长尾预测模型，使不同类别的分布尽可能相互区分。在三种架构上的八个长尾基准数据集上的实验表明，所提出的先知式范式为解决长尾数据集中类别知识有限这一挑战提供了有前景的解决方案。开发的代码已在 \url{https://github.com/tcmyxc/propheter} 公开。