In the quest for unveiling novel categories at test time, we confront the inherent limitations of traditional supervised recognition models that are restricted by a predefined category set. While strides have been made in the realms of self-supervised and open-world learning towards test-time category discovery, a crucial yet often overlooked question persists: what exactly delineates a category? In this paper, we conceptualize a category through the lens of optimization, viewing it as an optimal solution to a well-defined problem. Harnessing this unique conceptualization, we propose a novel, efficient and self-supervised method capable of discovering previously unknown categories at test time. A salient feature of our approach is the assignment of minimum length category codes to individual data instances, which encapsulates the implicit category hierarchy prevalent in real-world datasets. This mechanism affords us enhanced control over category granularity, thereby equipping our model to handle fine-grained categories adeptly. Experimental evaluations, bolstered by state-of-the-art benchmark comparisons, testify to the efficacy of our solution in managing unknown categories at test time. Furthermore, we fortify our proposition with a theoretical foundation, providing proof of its optimality. Our code is available at https://github.com/SarahRastegar/InfoSieve.

翻译：在测试时揭示新类别的探索中，我们直面传统监督识别模型因预设类别集约束而固有的局限性。尽管自监督学习和开放世界学习领域在测试时类别发现方面取得了进展，但一个关键却常被忽视的问题依然存在：究竟什么定义了一个类别？本文通过优化视角对类别进行概念化，将其视为定义明确问题的最优解。利用这一独特概念，我们提出了一种新颖、高效且自监督的方法，能够在测试时发现先前未知的类别。我们方法的一个显著特征是为每个数据实例分配最小长度的类别编码，这封装了现实数据集中普遍存在的隐式类别层次结构。这一机制赋予我们对类别粒度的增强控制，从而使模型能够灵活处理细粒度类别。实验评估结合顶尖基准对比，验证了我们的方案在应对测试时未知类别方面的有效性。此外，我们为这一主张提供了理论基础，并给出了其最优性的证明。我们的代码开源于 https://github.com/SarahRastegar/InfoSieve。