由部件级语义先验引导的弱监督可供性定位
Weakly-Supervised Affordance Grounding Guided by Part-Level Semantic Priors
AI总结：
针对弱监督可供性定位任务，提出基于伪标签的有监督训练流程，利用部件分割模型生成伪标签并引入标签细化、特征对齐和轻量级推理三项增强，有效弥合物体与动作间的差距并取得突破性性能提升。
摘要：
在本工作中，我们关注弱监督可供性定位任务，模型使用人-物交互图像和自我中心物体图像进行训练，无需密集标签即可识别物体上的可供性区域。先前的工作大多建立在类激活图之上，这对语义分割有效，但可能不适合定位动作和功能。利用近期先进的基础模型，我们开发了一种基于伪标签的有监督训练流程。伪标签由现成的部件分割模型生成，并由可供性到部件名称的映射进行引导。此外，我们为基线模型引入了三项关键增强：标签细化阶段、细粒度特征对齐过程和轻量级推理模块。这些技术利用现成基础模型中嵌入的静态物体的语义知识来改进可供性学习，有效弥合了物体与动作之间的差距。大量实验表明，所提出模型的性能相比现有方法取得了突破性提升。代码可在 https://github.com/woyut/WSAG-PLSP 获取。
英文摘要：
In this work, we focus on the task of weakly supervised affordance grounding, where a model is trained to identify affordance regions on objects using human-object interaction images and egocentric object images without dense labels. Previous works are mostly built upon class activation maps, which are effective for semantic segmentation but may not be suitable for locating actions and functions. Leveraging recent advanced foundation models, we develop a supervised training pipeline based on pseudo labels. The pseudo labels are generated from an off-the-shelf part segmentation model, guided by a mapping from affordance to part names. Furthermore, we introduce three key enhancements to the baseline model: a label refining stage, a fine-grained feature alignment process, and a lightweight reasoning module. These techniques harness the semantic knowledge of static objects embedded in off-the-shelf foundation models to improve affordance learning, effectively bridging the gap between objects and actions. Extensive experiments demonstrate that the performance of the proposed model has achieved a breakthrough improvement over existing methods. Our codes are available at https://github.com/woyut/WSAG-PLSP .
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。
