在持续广义类别发现中解耦发现与记忆
Decouple Your Discovery and Memory in Continual Generalized Category Discovery
双分支解耦思路可迁移到任何需要「边学新类边保旧类」的视觉识别场景：把发现分支与记忆分支分开，避免过度保护旧类压制新类发现，并可作为插件叠加到现有增量/开放世界识别框架上。
原文依据 we introduce the Decouple Your Discovery and Memory (DYDM), a dual-branch architecture that decouples the discovery of new classes and the memorization of old classes
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论持续广义类别发现（C-GCD）旨在从无标签数据中增量地发现新类别并记忆旧类别知识，从而提升模型在真实场景中的适应性。特别地，无标签数据同时来自旧类和新类，要求模型在发现新类的同时识别此前已学过的类别。为此，近期工作致力于设计特定框架与多种抗遗忘策略，力求实现典型的稳定性—可塑性权衡。与以往研究不同，本文首先重新审视这些方法，并指出其中大多数方法对旧类保护过度，妨碍了对新类的准确发现。为应对这一挑战，我们提出解耦发现与记忆（DYDM），一种将新类发现与旧类记忆解耦的双分支架构。发现分支专注于准确识别新类，而记忆分支以递归方式巩固所有已识别类别，并作为推理分支发挥作用。重要的是，得益于记忆分支强大的知识保持能力，发现分支能够促进从无标签数据中识别新类，从而在可塑性与稳定性之间取得双赢结果。在多种数据集与设置上的大量实验证明了本方法的优越性，领先幅度最高分别达到 9.87%、7.30%、3.18% 和 8.25%。此外，我们的框架可与现有方法集成，并持续提升其性能。
英文原文摘要 1600 字符
Continual Generalized Category Discovery (C-GCD) seeks to incrementally discover new categories from unlabeled data and memorize old categories' knowledge, fostering model adaptability in real-world scenarios. Especially, the unlabeled data is from both old and new classes, requiring the model to recognize previously learned classes while discovering. In response, recent efforts focus on devising specific frameworks and various anti-forgetting strategies, striving for a typical stability-plasticity trade-off. Unlike previous studies, in this work, we first revisit these methods and identify that most of these methods over-protect old classes, hampering the accurate discovery of novel ones. To address this challenge, we introduce the Decouple Your Discovery and Memory (DYDM), a dual-branch architecture that decouples the discovery of new classes and the memorization of old classes. The discovery branch is focused on accurately recognizing new classes, while the memory branch consolidates all identified categories in a recursive manner and functions as the inference branch. Importantly, benefiting from the strong knowledge retention ability of the memory branch, the discovery branch can facilitate the recognition of novel classes from the unlabeled data, achieving a win-win outcome between plasticity and stability. Extensive experiments on various datasets and settings demonstrate the superiority of our approach, achieving leads of up to 9.87%, 7.30%, 3.18%, and 8.25%. Furthermore, our framework can integrate with existing approaches, consistently enhancing their performance.