ClearGCD: 缓解捷径学习以实现稳健的通用类别发现
ClearGCD: Mitigating Shortcut Learning For Robust Generalized Category Discovery
浏览论文内容
中文总结 AI 辅助
ClearGCD通过语义对齐和捷径抑制正则化缓解捷径学习，提升通用类别发现的稳健性和泛化能力。
中文摘要 AI 辅助
在开放世界场景中，通用类别发现（GCD）需要在未标记数据中识别已知和新类别。然而，现有方法常因捷径学习导致原型混淆，影响泛化能力并导致已知类别的遗忘。我们提出了ClearGCD，一个旨在通过两种互补机制减少对非语义线索依赖的框架。首先，语义视图对齐（SVA）通过跨类补丁替换生成强增强，并利用弱增强强制语义一致性。其次，捷径抑制正则化（SSR）维护一个自适应原型库，对齐已知类别同时鼓励潜在新类别的分离。ClearGCD可无缝集成到参数化GCD方法中，并在多个基准上一致优于最新方法。
英文摘要
In open-world scenarios, Generalized Category Discovery (GCD) requires identifying both known and novel categories within unlabeled data. However, existing methods often suffer from prototype confusion caused by shortcut learning, which undermines generalization and leads to forgetting of known classes. We propose ClearGCD, a framework designed to mitigate reliance on non-semantic cues through two complementary mechanisms. First, Semantic View Alignment (SVA) generates strong augmentations via cross-class patch replacement and enforces semantic consistency using weak augmentations. Second, Shortcut Suppression Regularization (SSR) maintains an adaptive prototype bank that aligns known classes while encouraging separation of potential novel ones. ClearGCD can be seamlessly integrated into parametric GCD approaches and consistently outperforms state-of-the-art methods across multiple benchmarks.
发表机构
- Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
- School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
- Loughborough University（洛桑大学）
机构由 AI 辅助整理，请以论文原文为准。
