学习多样化与聚焦：面向开放词表人-物交互检测的强化学习框架
Learning to Diversify and Focus: A Reinforcement Framework for Open-Vocabulary HOI Detection
用强化学习驱动的语义扰动与 actor-critic 注意力精炼，缓解 CLIP 一阶段范式对已见交互的过拟合，可直接迁移到其他开放词表检测/grounding 任务中提升对未见类别的泛化与细粒度定位。
原文依据 we propose a novel Semantic-Diversified and Interaction-Focused framework (SD-IF), which integrates reinforcement-guided adaptive optimization
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论开放词表人-物交互（OV-HOI）检测旨在识别训练集之外的新颖 HOI 类别。现有 OV-HOI 检测方法通常利用 CLIP 提取全局视觉表示，并在可学习查询与全局特征之间执行交叉注意力以定位人-物对。然而，此类一阶段范式容易对已见交互过拟合，从而限制其对未见类别的泛化能力；同时 CLIP 粗粒度的空间感知也阻碍了细粒度交互线索的定位。为解决这些问题，我们提出一种新颖的语义多样化与交互聚焦框架（SD-IF），它集成强化引导的自适应优化，以联合增强语义泛化与空间判别能力。具体而言，我们引入语义多样化（SD）模块，该模块施加强化驱动的随机语义扰动与双层语义探索，在保持视觉一致性的同时扩展查询的语义覆盖范围，并有效鼓励对已见语义簇之外的探索。此外，我们设计交互聚焦（IF）模块，构建 actor-critic 优化方案，在由空间聚焦与语义一致性组成的混合奖励引导下，基于检测特征与交互表示自适应地精炼注意力分布。在两个标准基准上的大量实验证明了 SD-IF 的有效性。
英文原文摘要 1511 字符
Open-Vocabulary Human-Object Interaction (OV-HOI) detection aims to recognize novel HOI categories beyond the training set. Existing OV-HOI detection approaches typically leverage CLIP to extract global visual representations and perform cross-attention between learnable queries and global features to localize human-object pairs. However, such one-stage paradigms tend to overfit seen interactions, limiting their generalization to unseen categories, while the coarse spatial awareness of CLIP also hinders the localization of fine-grained interaction cues. To address these issues, we propose a novel Semantic-Diversified and Interaction-Focused framework (SD-IF), which integrates reinforcement-guided adaptive optimization to jointly enhance semantic generalization and spatial discrimination. Specifically, we introduce a Semantic Diversification (SD) module that applies reinforcement-driven stochastic semantic perturbations and dual-level semantic exploration, expanding the semantic coverage of queries while maintaining visual coherence and effectively encouraging exploration beyond the seen semantic clusters. Furthermore, we design an Interaction Focusing (IF) module that formulates an actor-critic optimization scheme to adaptively refine attention distributions based on detection features and interaction representations, guided by a hybrid reward combining spatial focusing and semantic consistency. Extensive experiments on two standard benchmarks demonstrate the effectiveness of our SD-IF.