RegFormer：可转移的交互关系接地以实现高效的弱监督人类-物体交互检测
RegFormer: Transferable Relational Grounding for Efficient Weakly-Supervised Human-Object Interaction Detection
AI总结：
RegFormer通过空间接地信号实现高效的弱监督人类-物体交互检测，无需额外训练即可直接迁移至实例级推理，实验表明其在效率和性能上均优于传统方法。
摘要：
弱监督人类-物体交互（HOI）检测对于可扩展的场景理解至关重要，因为它仅通过图像级注释学习交互。由于缺乏定位信号，先前的工作通常依赖外部物体检测器生成候选对，然后通过成对推理推断其交互。然而，这种框架在扩展时往往因枚举大量实例对而产生巨大的计算成本。此外，它还受到非交互组合导致的假阳性影响，阻碍了准确的实例级HOI推理。为了解决这些问题，我们引入了关系接地变换器（RegFormer），一种多功能的交互识别模块，用于高效且准确的HOI推理。在图像级监督下，RegFormer利用空间接地信号作为推理过程的指导，并促进局部意识的交互学习。通过学习局部化交互线索，我们的模块区分了人类、物体及其交互，使模块能够从图像级交互推理直接转移到精确且高效的实例级推理，而无需额外训练。我们的广泛实验和分析表明，RegFormer有效学习了实例级交互推理的空间线索，具有高效率，并且甚至实现了与全监督模型相当的性能。我们的代码可在https://github.com/mlvlab/RegFormer上获得。
英文摘要：
Weakly-supervised Human-Object Interaction (HOI) detection is essential for scalable scene understanding, as it learns interactions from only image-level annotations. Due to the lack of localization signals, prior works typically rely on an external object detector to generate candidate pairs and then infer their interactions through pairwise reasoning. However, this framework often struggles to scale due to the substantial computational cost incurred by enumerating numerous instance pairs. In addition, it suffers from false positives arising from non-interactive combinations, which hinder accurate instance-level HOI reasoning. To address these issues, we introduce Relational Grounding Transformer (RegFormer), a versatile interaction recognition module for efficient and accurate HOI reasoning. Under image-level supervision, RegFormer leverages spatially grounded signals as guidance for the reasoning process and promotes locality-aware interaction learning. By learning localized interaction cues, our module distinguishes humans, objects, and their interactions, enabling direct transfer from image-level interaction reasoning to precise and efficient instance-level reasoning without additional training. Our extensive experiments and analyses demonstrate that RegFormer effectively learns spatial cues for instance-level interaction reasoning, operates with high efficiency, and even achieves performance comparable to fully supervised models. Our code is available at https://github.com/mlvlab/RegFormer.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
