穿透分布偏移：因果启发的鲁棒广义类别发现
Seeing Through the Shift: Causality-Inspired Robust Generalized Category Discovery
把因果图与因果依赖风险估计引入跨域广义类别发现，用流形层面的不变性约束对齐已知/未知类，可作为处理域偏移下开放世界表征学习的通用正则手段。
原文依据 we propose a Causal Geometric Manifold Constraint that enforces invariant manifold-level associations between known and unknown categories across domains
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论广义类别发现（GCD）旨在将已知类别的知识迁移到自动发现新的、未见过的类别上，同时保持对已知类别的识别能力。尽管近期取得了进展，现有 GCD 方法通常假设所有数据来自同一分布，而这在真实场景中很少成立。实践中，数据往往同时经历域偏移与新类别涌现，导致现有系统性能严重下降。为应对这一挑战，我们提出 CausalGCD，一个受因果启发的框架，旨在缓解类别发现中的域偏移偏差。具体而言，我们首先分析因果图，以揭示跨域 GCD 中关键变量之间的关系。随后，我们引入因果依赖风险的概念，并提出因果依赖风险估计器以捕捉因果语义，进一步推导出一个理论上可计算的上界，用于在跨域 GCD 设定下优化该风险。此外，我们提出因果几何流形约束，强制已知与未知类别在跨域之间建立不变的流形级关联，从而促进对新类别的鲁棒发现。在 SSB-C 与 DomainNet 基准上的大量实验证明了 CausalGCD 的有效性，并凸显了因果推理在开放世界类别发现中的重要意义。
英文原文摘要 1411 字符
Generalized Category Discovery (GCD) aims to transfer knowledge from known categories to automatically discover new, unseen ones while preserving recognition of the known classes. Despite recent progress, existing GCD approaches typically assume that all data are drawn from the same distribution, which is rarely valid in real-world scenarios. In practice, data often experience simultaneous domain shifts and novel category emergence, causing severe performance degradation of existing systems. To address this challenge, we propose CausalGCD, a causality-inspired framework designed to mitigate domain-shift bias in category discovery. Specifically, we first analyze the causal graph to uncover the relationships among key variables in cross-domain GCD. We then introduce the concept of causal dependency risk and propose a Causal Dependency Risk Estimator to capture causal semantics, further deriving a theoretically computable upper bound to optimize this risk under cross-domain GCD settings. Furthermore, we propose a Causal Geometric Manifold Constraint that enforces invariant manifold-level associations between known and unknown categories across domains, thereby facilitating robust discovery of novel classes. Extensive experiments on the SSB-C and DomainNet benchmarks demonstrate the effectiveness of CausalGCD and highlight the significance of causal reasoning in open-world category discovery.