Generalized Category Discovery (GCD) focuses on classifying known categories while simultaneously discovering novel categories from unlabeled data. However, previous GCD methods face challenges due to inconsistent optimization objectives and category confusion. This leads to feature overlap and ultimately hinders performance on novel categories. To address these issues, we propose the Neural Collapse-inspired Generalized Category Discovery (NC-GCD) framework. By pre-assigning and fixing Equiangular Tight Frame (ETF) prototypes, our method ensures an optimal geometric structure and a consistent optimization objective for both known and novel categories. We introduce a Consistent ETF Alignment Loss that unifies supervised and unsupervised ETF alignment and enhances category separability. Additionally, a Semantic Consistency Matcher (SCM) is designed to maintain stable and consistent label assignments across clustering iterations. Our method achieves strong performance on multiple GCD benchmarks, significantly enhancing novel category accuracy and demonstrating its effectiveness.

翻译：广义类别发现（GCD）旨在对已知类别进行分类的同时，从无标注数据中发现新类别。然而，现有GCD方法因优化目标不一致和类别混淆问题面临挑战，导致特征重叠并最终影响新类别的识别性能。为解决这些问题，本文提出基于神经坍缩的广义类别发现（NC-GCD）框架。通过预分配并固定等角紧框架（ETF）原型，本方法为已知和新类别构建了最优几何结构与一致的优化目标。我们提出一致ETF对齐损失函数，统一有监督与无监督的ETF对齐过程以增强类别可分性。此外，设计了语义一致性匹配器（SCM）来维持聚类迭代过程中标签分配的稳定性与一致性。本方法在多个GCD基准测试中取得优异性能，显著提升新类别识别准确率，验证了其有效性。