发表机构
ÉTS Montréal（蒙特利尔高等工程技术学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对测试时适应与广义类别发现分离的问题，提出TT-GCD统一场景及PACT无监督框架，通过原型分配实现已知类别识别与新类别发现，在多个基准上优于现有方法。
AI 中文摘要
测试时适应（TTA）和广义类别发现（GCD）传统上被视为两个不相关的问题：前者假设所有测试类别已知，使模型适应域偏移；后者假设已知类别有标注训练数据，从而发现新类别。然而，现实世界的部署很少完全符合这两种设定。基于这一差距，我们引入了测试时广义类别发现（TT-GCD），这是一个统一且更现实的场景，其中视觉-语言模型必须在测试期间、无标注数据的情况下，适应分布偏移、仅使用文本监督对已知类别进行分类，并发现新类别。为应对这一挑战性场景，我们提出了PACT（测试时类别发现的原型分配），一个完全无监督的框架，通过原型分配实现已知类别识别和新类别发现。PACT首先利用高置信度的零样本预测，将偏移的视觉特征与VLM的文本派生类别表示重新对齐。然后，已知和新类别均由视觉嵌入空间中的原型表示，这些原型从无标注测试流中估计，每个测试图像被分配给其视觉特征与原型最相似的类别。在损坏和域偏移基准上的大量实验表明，PACT优于改编后的最先进TTA和GCD方法，有效弥合了适应与发现之间的差距。
英文摘要
Test-Time Adaptation (TTA) and Generalized Category Discovery (GCD) are traditionally treated as disjoint problems: the former adapts models to domain shift assuming all test classes are known, while the latter discovers novel categories assuming labeled training data for known classes. However, real-world deployment rarely fits either setting. Motivated by this gap, we introduce Test-Time Generalized Category Discovery (TT-GCD), a unified and more realistic scenario where a vision-language model must adapt to distribution shifts, classify known categories using only textual supervision, and discover novel categories, all during test time and without access to labeled data. To address this challenging scenario, we propose PACT (Prototype Assignment for Category discovery at Test time), a fully unsupervised framework that casts known-class recognition and novel-class discovery via prototype assignment. PACT first re-aligns shifted visual features with the text-derived class representations of the VLM using confident zero-shot predictions. Known and novel categories are then both represented by prototypes in the visual embedding space, estimated from the unlabeled test stream, and each test image is assigned to the category whose prototype is most similar to its visual feature. Extensive experiments across corruption and domain-shift benchmarks demonstrate that PACT outperforms adapted state-of-the-art TTA and GCD methods, effectively bridging the gap between adaptation and discovery.
