开放世界半监督新类发现
Open-world Semi-supervised Novel Class Discovery
AI总结：
本文提出OpenNCD方法，通过基于多原型的渐进式双层对比学习，在开放世界半监督场景下同时识别已知类并发现未知新类，有效应对标签稀缺问题。
摘要：
传统半监督学习任务假设有标签和无标签数据遵循相同的类别分布，但现实的开放世界场景更为复杂，未知新类混入无标签集中。因此，不仅要识别已知类样本，还要在无标签数据中发现未知数量的新类，极具挑战。本文提出一种新的开放世界半监督新类发现方法OpenNCD，这是一种基于多原型的渐进式双层对比学习方法。该方法由两部分相互增强组成。首先，引入双层对比学习方法，在原型对和原型组两个层级上维持相似性，以实现更好的表示学习。然后，基于共同表示实例提出一种可靠的原型相似度度量。高相似度的原型将渐进分组，用于已知类识别和新类发现。在三个图像数据集上进行了大量实验，结果表明该方法在开放世界场景中有效，尤其在已知类和标签稀缺时。
英文摘要：
Traditional semi-supervised learning tasks assume that both labeled and unlabeled data follow the same class distribution, but the realistic open-world scenarios are of more complexity with unknown novel classes mixed in the unlabeled set. Therefore, it is of great challenge to not only recognize samples from known classes but also discover the unknown number of novel classes within the unlabeled data. In this paper, we introduce a new open-world semi-supervised novel class discovery approach named OpenNCD, a progressive bi-level contrastive learning method over multiple prototypes. The proposed method is composed of two reciprocally enhanced parts. First, a bi-level contrastive learning method is introduced, which maintains the pair-wise similarity of the prototypes and the prototype group levels for better representation learning. Then, a reliable prototype similarity metric is proposed based on the common representing instances. Prototypes with high similarities will be grouped progressively for known class recognition and novel class discovery. Extensive experiments on three image datasets are conducted and the results show the effectiveness of the proposed method in open-world scenarios, especially with scarce known classes and labels.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
