用类比生成文本概念，让模型更好区分相似新类别
Learning Like Humans: Analogical Concept Learning for Generalized Category Discovery
- 通过类比已有知识生成新样本的文本描述
- 在六个基准上提升新旧类别识别准确率，细粒度数据效果更明显
- 可无缝接入现有发现框架，适合做开放世界分类的场景
通用类别发现（GCD）旨在无标签数据中识别新类别，同时保持对已知类别的识别能力。然而，当前仅依赖视觉的流程与监督学习耦合松散，导致细粒度、外观相似类别的边界模糊。本文提出类比文本概念生成器（ATCG），通过将已有标注知识类比到未标注样本，为新数据生成文本概念。将这些类比生成的文本概念与视觉特征融合，使发现过程变为跨模态推理，实现先验知识向新数据的迁移，增强类别分离。ATCG可适配参数化和聚类型的GCD方法，无需修改原有结构。在六个基准测试中，ATCG稳定提升整体性能、已知类别和新类别识别率，尤其在细粒度数据上增益最大。
原文摘要 · Abstract (English)
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. Our code is available at: https://github.com/zhou-9527/AnaLogical-GCD.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。