超语义空间中面向即时类别发现的分配驱动哈希学习
Assignment-Driven Hash Learning in a Hyper-Semantic Space for On-the-Fly Category Discovery
把「超语义空间」的双几何子空间（父原型派生增强 + 跨原型插值校准）与灵活原型分配、二值哈希正则化结合，可作为即插即用模块嵌入现有开放世界/流式类别发现流程，缓解已知类对新类的空间垄断与特征到哈希的级联退化。
原文依据 Our framework serves as a plug-and-play module, consistently improving state-of-the-art OCD methods across fine-grained benchmarks.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论即时类别发现（OCD）旨在仅利用少量已标注类别提供的监督，从流式数据中动态识别已知类别与新兴的未知类别。尽管近期取得了进展，我们的实证分析揭示了其根本性局限：现有方法存在从特征到哈希的级联退化，以及已知类别对空间的严重垄断，从根本上阻碍了新类别的发现。为应对这些相互耦合的挑战，我们提出了一个有原则的两阶段框架。我们首先构建一个具有对偶几何子空间的超语义空间：派生自空间采用父原型派生的原型增强，以捕捉类内多样性并增强类间判别性；校准子空间通过跨原型插值合成，以施加分布约束并防止表征坍缩。在这一几何约束的空间内，我们执行分配驱动的哈希学习，其中灵活原型分配（FPA）建模类内变化并增强类间分离，同时二值哈希正则化（BHR）强制形成紧凑且具判别性的哈希表征。我们的框架可作为即插即用模块，在细粒度基准上持续提升最优的 OCD 方法。代码将在论文录用后发布。
英文原文摘要 1357 字符
On-the-fly Category Discovery (OCD) aims to dynamically identify both known and emerging unknown categories from streaming data, using supervision from only a limited set of labeled classes. Despite recent progress, our empirical analysis reveals fundamental limitations: existing methods suffer from cascading feature-to-hash degradation and severe space monopolization by known classes, fundamentally hindering novel category discovery. To address these coupled challenges, we introduce a principled two-stage framework.We first construct a Hyper-Semantic Space with dual geometric subspaces: a Derived Subspace employing parent-derived prototype augmentation to capture intra-class diversity and enhance inter-class discrimination, and a Calibrated Subspace synthesized through cross-prototype interpolation to impose distributional constraints and prevent representational collapse.Within this geometrically-constrained space, we perform Assignment-Driven Hash Learning, where Flexible Prototype Assignment (FPA) models intra-class variations and enhances inter-class separation, alongside Binary Hash Regularization (BHR) to enforce compact and discriminative hash representations. Our framework serves as a plug-and-play module, consistently improving state-of-the-art OCD methods across fine-grained benchmarks. Code will be released upon acceptance.