像人类一样学习：面向广义类别发现的类比概念学习
Learning Like Humans: Analogical Concept Learning for Generalized Category Discovery
把无标注样本的发现过程转成视觉-文本推理：用已标注知识类比生成文本概念，再与视觉特征融合，可直接插到参数化或聚类式 GCD 流程中，为开放世界细粒度识别提供可复用的文本先验注入手段。
原文依据 Fusing these analogical textual concepts with visual features turns discovery into a visual-textual reasoning process
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论广义类别发现（GCD）旨在从无标注数据中发现新类别，同时保持对已知类别的识别能力；然而，当前主流的纯视觉流程以及监督学习与发现过程之间的松散耦合，往往在细粒度、外观相似的类别上产生脆弱的决策边界。我们提出类比文本概念生成器（ATCG），这是一个即插即用模块，它从已标注知识进行类比，迁移到新的观测上，为无标注样本形成文本概念。将这些类比文本概念与视觉特征融合，使发现过程转变为视觉-文本推理过程，从而把先验知识迁移到新数据并锐化类别分离。ATCG 可同时挂接到参数化式与聚类式 GCD 流程，且无需改动其整体设计。在六个基准上，ATCG 一致地提升整体、已知类与新类性能，其中在细粒度数据上增益最大。
英文原文摘要 965 字符
Generalized Category Discovery (GCD) seeks to uncover novel categories in unlabeled data while preserving recognition of known categories, yet prevailing visual-only pipelines and the loose coupling between supervised learning and discovery often yield brittle boundaries on fine-grained, look-alike categories. We introduce the Analogical Textual Concept Generator (ATCG), a plug-and-play module that analogizes from labeled knowledge to new observations, forming textual concepts for unlabeled samples. Fusing these analogical textual concepts with visual features turns discovery into a visual-textual reasoning process, transferring prior knowledge to novel data and sharpening category separation. ATCG attaches to both parametric and clustering style GCD pipelines and requires no changes to their overall design. Across six benchmarks, ATCG consistently improves overall, known-class, and novel-class performance, with the largest gains on fine-grained data.