ProtoGCD：面向广义类别发现的统一无偏原型学习

ProtoGCD: Unified and Unbiased Prototype Learning for Generalized Category Discovery

April 2, 2025

作者: Shijie Ma, Fei Zhu, Xu-Yao Zhang, Cheng-Lin Liu

cs.AI

摘要

广义类别发现（GCD）是一个实用但尚未充分探索的问题，它要求模型通过利用旧类别的标注样本来自动聚类并发现新类别。其挑战在于未标注数据中同时包含旧类别和新类别。早期工作采用参数化分类器进行伪标签处理，将旧类别和新类别分开处理，导致两者之间的准确率失衡。最近的方法利用对比学习，却忽视了潜在的正面样本，并与聚类目标脱节，导致表示偏差和次优结果。为解决这些问题，我们引入了一个统一且无偏的原型学习框架，即ProtoGCD，其中旧类别和新类别通过联合原型和统一学习目标进行建模，实现了新旧类别的统一建模。具体而言，我们提出了一种双层次自适应伪标签机制来缓解确认偏差，并结合两个正则化项共同帮助学习更适合GCD的表示。此外，出于实际考虑，我们设计了一个准则来估计新类别的数量。更进一步，我们将ProtoGCD扩展至检测未见过的异常值，实现了任务层面的统一。综合实验表明，ProtoGCD在通用和细粒度数据集上均达到了最先进的性能。代码可在https://github.com/mashijie1028/ProtoGCD获取。

English

Generalized category discovery (GCD) is a pragmatic but underexplored problem, which requires models to automatically cluster and discover novel categories by leveraging the labeled samples from old classes. The challenge is that unlabeled data contain both old and new classes. Early works leveraging pseudo-labeling with parametric classifiers handle old and new classes separately, which brings about imbalanced accuracy between them. Recent methods employing contrastive learning neglect potential positives and are decoupled from the clustering objective, leading to biased representations and sub-optimal results. To address these issues, we introduce a unified and unbiased prototype learning framework, namely ProtoGCD, wherein old and new classes are modeled with joint prototypes and unified learning objectives, {enabling unified modeling between old and new classes}. Specifically, we propose a dual-level adaptive pseudo-labeling mechanism to mitigate confirmation bias, together with two regularization terms to collectively help learn more suitable representations for GCD. Moreover, for practical considerations, we devise a criterion to estimate the number of new classes. Furthermore, we extend ProtoGCD to detect unseen outliers, achieving task-level unification. Comprehensive experiments show that ProtoGCD achieves state-of-the-art performance on both generic and fine-grained datasets. The code is available at https://github.com/mashijie1028/ProtoGCD.