Generalized category discovery (GCD) is a recently proposed open-world task. Given a set of images consisting of labeled and unlabeled instances, the goal of GCD is to automatically cluster the unlabeled samples using information transferred from the labeled dataset. The unlabeled dataset comprises both known and novel classes. The main challenge is that unlabeled novel class samples and unlabeled known class samples are mixed together in the unlabeled dataset. To address the GCD without knowing the class number of unlabeled dataset, we propose a co-training-based framework that encourages clustering consistency. Specifically, we first introduce weak and strong augmentation transformations to generate two sufficiently different views for the same sample. Then, based on the co-training assumption, we propose a consistency representation learning strategy, which encourages consistency between feature-prototype similarity and clustering assignment. Finally, we use the discriminative embeddings learned from the semi-supervised representation learning process to construct an original sparse network and use a community detection method to obtain the clustering results and the number of categories simultaneously. Extensive experiments show that our method achieves state-of-the-art performance on three generic benchmarks and three fine-grained visual recognition datasets. Especially in the ImageNet-100 data set, our method significantly exceeds the best baseline by 15.5\% and 7.0\% on the \texttt{Novel} and \texttt{All} classes, respectively.

翻译：广义类别发现（GCD）是近期提出的开放世界任务。给定包含有标注和无标注实例的图像集合，GCD的目标是通过从标注数据集中迁移信息，自动对无标注样本进行聚类。无标注数据集同时包含已知类和未知类。主要挑战在于无标注数据集中混合了未知类样本和已知类样本。为在未知数据集类别数量的条件下解决GCD问题，我们提出基于协同训练的框架来促进聚类一致性。具体而言，我们首先引入弱增强和强增强变换，为同一样本生成两个充分不同的视图。接着基于协同训练假设，提出一致性表征学习策略，该策略鼓励特征-原型相似度与聚类分配之间的一致性。最后，利用半监督表征学习过程获得的判别性嵌入构建原始稀疏网络，通过社区检测方法同时获取聚类结果与类别数量。大量实验表明，我们的方法在三个通用基准数据集和三个细粒度视觉识别数据集上均达到最先进性能。特别是在ImageNet-100数据集中，本方法在\texttt{Novel}和\texttt{All}类别上分别超越最佳基线15.5%和7.0%。