TALON：实时适应学习用于即时类别发现
TALON: Test-time Adaptive Learning for On-the-Fly Category Discovery
AI总结：
TALON通过实时适应学习实现即时类别发现，结合语义感知原型更新和稳定测试时间编码器更新，有效提升分类性能并缓解类别爆炸问题。
摘要：
实时类别发现（OCD）旨在在识别已知类别的同时，从未标记的在线流中发现新的类别，使用仅在标记数据上训练的模型。现有方法冻结了离线训练的特征提取器，并采用基于哈希的框架，将特征量化为二进制代码作为类原型。然而，使用固定知识库发现新类别是反直觉的，因为输入数据的学习潜力被完全忽视。此外，特征量化引入了信息损失，削弱了表示的表达能力，并放大了类内方差。这常常导致类别爆炸，即一个类别被分割成多个伪类别。为克服这些限制，我们提出了一种测试时间适应框架，使模型能够通过发现进行学习。它结合了两种互补策略：语义感知的原型更新和稳定的测试时间编码器更新。前者动态优化类原型以提高分类性能，后者将新信息直接整合到参数空间中。共同作用下，这些组件使模型能够通过新遇到的样本不断扩展其知识库。此外，我们引入了一种基于边距的logit校准，在离线阶段扩大类间边距并提高类内紧凑性，从而为未来的类别发现保留嵌入空间。在标准OCD基准测试中，我们的方法显著优于现有基于哈希的最先进方法，实现了显著的新型类别准确率提升，并有效缓解了类别爆炸问题。代码已公开在https://github.com/ynanwu/TALON。
英文摘要：
On-the-fly category discovery (OCD) aims to recognize known categories while simultaneously discovering novel ones from an unlabeled online stream, using a model trained only on labeled data. Existing approaches freeze the feature extractor trained offline and employ a hash-based framework that quantizes features into binary codes as class prototypes. However, discovering novel categories with a fixed knowledge base is counterintuitive, as the learning potential of incoming data is entirely neglected. In addition, feature quantization introduces information loss, diminishes representational expressiveness, and amplifies intra-class variance. It often results in category explosion, where a single class is fragmented into multiple pseudo-classes. To overcome these limitations, we propose a test-time adaptation framework that enables learning through discovery. It incorporates two complementary strategies: a semantic-aware prototype update and a stable test-time encoder update. The former dynamically refines class prototypes to enhance classification, whereas the latter integrates new information directly into the parameter space. Together, these components allow the model to continuously expand its knowledge base with newly encountered samples. Furthermore, we introduce a margin-aware logit calibration in the offline stage to enlarge inter-class margins and improve intra-class compactness, thereby reserving embedding space for future class discovery. Experiments on standard OCD benchmarks demonstrate that our method substantially outperforms existing hash-based state-of-the-art approaches, yielding notable improvements in novel-class accuracy and effectively mitigating category explosion. The code is publicly available at \textcolor{blue}{https://github.com/ynanwu/TALON}.
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。
