用多样大模型反馈主动发现新类别，减少人工标注依赖。
GLEAN: Active Generalized Category Discovery with Diverse LLM Feedback
- 通过三种大模型反馈优化特征、生成描述、对齐不确定样本
- 在多个数据集上超越现有方法，显著提升新类别识别率
- 适合需要低成本标注的开放世界场景应用
广义类别发现（GCD）是一项实用且具有挑战性的开放世界任务，旨在仅用少量已知类别的标注数据，识别未标记数据中的已知和新类别。由于缺乏监督，现有方法难以纠正混淆样本错误，也无法有效挖掘和利用发现聚类的语义信息，因此通常需额外标注才能实际应用。然而人工标注成本高、效率低。为此，我们提出GLEAN，一个统一的广义类别发现框架，可主动学习来自多样化协同大模型的反馈。该方法利用三种不同类型的LLM反馈：(1) 改进实例级对比特征；(2) 生成类别描述；(3) 将不确定样本与大模型选定的类别描述对齐。大量实验表明，GLEAN在多种数据集、评估指标和监督设置下均优于当前最优模型。代码已开源：https://github.com/amazon-science/Glean。
原文摘要 · Abstract (English)
Generalized Category Discovery (GCD) is a practical and challenging open-world task that aims to recognize both known and novel categories in unlabeled data using limited labeled data from known categories. Due to the lack of supervision, previous GCD methods face significant challenges, such as difficulty in rectifying errors for confusing instances, and inability to effectively uncover and leverage the semantic meanings of discovered clusters. Therefore, additional annotations are usually required for real-world applicability. However, human annotation is extremely costly and inefficient. To address these issues, we propose GLEAN, a unified framework for generalized category discovery that actively learns from diverse and collaborative LLM feedback. Our approach leverages three different types of LLM feedback to: (1) improve instance-level contrastive features, (2) generate category descriptions, and (3) align uncertain instances with LLM-selected category descriptions. Extensive experiments demonstrate the superior performance of GLEAN over state-of-the-art models across diverse datasets, metrics, and supervision settings. Our code is available at https://github.com/amazon-science/Glean.
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。