解决长尾分布下的未知类别发现问题，提升真实数据场景的识别效果。
Long-Tailed Learning for Generalized Category Discovery
- 用可学习分布自动生成伪标签，减少分类器偏差
- 通过邻域挖掘增强尾部类别的特征区分性
- 适用于真实世界数据，尤其对少数类识别更有效
通用类别发现（GCD）利用已知类别的有标签样本，在无标签样本中发现新类别。现有方法在人工构造的平衡数据集上表现良好，但在真实世界数据中普遍存在类别不平衡问题，严重影响其性能。为此，我们提出一种在长尾分布下进行通用类别发现的新框架。首先引入自引导标注技术，利用可学习分布生成伪标签，从而获得更少偏差的分类器；随后设计表示平衡机制，通过挖掘样本邻域，促使模型更关注尾部类别，获得更具区分性的特征表示。我们在多个公开数据集上进行了实验，结果表明所提方法优于现有最先进方法。
原文摘要 · Abstract (English)
Generalized Category Discovery (GCD) utilizes labeled samples of known classes to discover novel classes in unlabeled samples. Existing methods show effective performance on artificial datasets with balanced distributions. However, real-world datasets are always imbalanced, significantly affecting the effectiveness of these methods. To solve this problem, we propose a novel framework that performs generalized category discovery in long-tailed distributions. We first present a self-guided labeling technique that uses a learnable distribution to generate pseudo-labels, resulting in less biased classifiers. We then introduce a representation balancing process to derive discriminative representations. By mining sample neighborhoods, this process encourages the model to focus more on tail classes. We conduct experiments on public datasets to demonstrate the effectiveness of the proposed framework. The results show that our model exceeds previous state-of-the-art methods.
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。