This paper investigates the problem of Generalized Category Discovery (GCD). Given a partially labelled dataset, GCD aims to categorize all unlabelled images, regardless of whether they belong to known or unknown classes. Existing approaches typically depend on either single-level semantics or manually designed abstract hierarchies, which limit their generalizability and scalability. To address these limitations, we introduce a SEmantic-aware hierArchical Learning framework (SEAL), guided by naturally occurring and easily accessible hierarchical structures. Within SEAL, we propose a Hierarchical Semantic-Guided Soft Contrastive Learning approach that exploits hierarchical similarity to generate informative soft negatives, addressing the limitations of conventional contrastive losses that treat all negatives equally. Furthermore, a Cross-Granularity Consistency (CGC) module is designed to align the predictions from different levels of granularity. SEAL consistently achieves state-of-the-art performance on fine-grained benchmarks, including the SSB benchmark, Oxford-Pet, and the Herbarium19 dataset, and further demonstrates generalization on coarse-grained datasets. Project page: https://visual-ai.github.io/seal/

翻译：本文研究广义类别发现（GCD）问题。给定部分标注的数据集，GCD旨在对所有未标注图像进行分类，无论其属于已知类别还是未知类别。现有方法通常依赖于单层语义或人工设计的抽象层次结构，限制了其泛化能力和可扩展性。为解决这些局限性，我们引入了一种由自然存在且易于获取的层次结构引导的语义感知分层学习框架（SEAL）。在该框架中，我们提出了一种分层语义引导的软对比学习方法，该方法利用层次相似性生成信息丰富的软负样本，解决了传统对比损失平等对待所有负样本的局限性。此外，我们设计了跨粒度一致性（CGC）模块，用于对齐不同粒度级别的预测结果。SEAL在细粒度基准测试（包括SSB基准、Oxford-Pet和Herbarium19数据集）上持续取得最先进的性能，并在粗粒度数据集上进一步展示了泛化能力。项目页面：https://visual-ai.github.io/seal/