Weakly-Supervised Scene Graph Generation (WSSGG) research has recently emerged as an alternative to the fully-supervised approach that heavily relies on costly annotations. In this regard, studies on WSSGG have utilized image captions to obtain unlocalized triplets while primarily focusing on grounding the unlocalized triplets over image regions. However, they have overlooked the two issues involved in the triplet formation process from the captions: 1) Semantic over-simplification issue arises when extracting triplets from captions, where fine-grained predicates in captions are undesirably converted into coarse-grained predicates, resulting in a long-tailed predicate distribution, and 2) Low-density scene graph issue arises when aligning the triplets in the caption with entity/predicate classes of interest, where many triplets are discarded and not used in training, leading to insufficient supervision. To tackle the two issues, we propose a new approach, i.e., Large Language Model for weakly-supervised SGG (LLM4SGG), where we mitigate the two issues by leveraging the LLM's in-depth understanding of language and reasoning ability during the extraction of triplets from captions and alignment of entity/predicate classes with target data. To further engage the LLM in these processes, we adopt the idea of Chain-of-Thought and the in-context few-shot learning strategy. To validate the effectiveness of LLM4SGG, we conduct extensive experiments on Visual Genome and GQA datasets, showing significant improvements in both Recall@K and mean Recall@K compared to the state-of-the-art WSSGG methods. A further appeal is that LLM4SGG is data-efficient, enabling effective model training with a small amount of training images.

翻译：弱监督场景图生成（WSSGG）研究近期作为全监督方法的替代方案兴起，后者严重依赖昂贵的标注。现有WSSGG研究利用图像描述获取非定位三元组，重点解决如何将这些三元组与图像区域对齐的问题。然而，这些工作忽略了从描述中生成三元组时涉及的两个问题：1）从描述中提取三元组时存在语义过度简化问题，描述中的细粒度谓词被不当转换为粗粒度谓词，导致谓词分布呈现长尾特征；2）将描述中的三元组与目标实体/谓词类别对齐时出现低密度场景图问题，大量三元组被丢弃而无法用于训练，造成监督信号不足。为解决这两个问题，我们提出新方法LLM4SGG（面向弱监督场景图生成的大型语言模型），该方法在从描述中提取三元组及将实体/谓词类别与目标数据对齐时，利用大型语言模型对语言的深度理解和推理能力来缓解上述问题。为进一步发挥LLM的作用，我们引入思维链思想和情境化小样本学习策略。通过在Visual Genome和GQA数据集上的大量实验，我们验证了LLM4SGG的有效性，其在Recall@K和平均Recall@K指标上均显著优于现有最优WSSGG方法。此外，LLM4SGG具有数据高效性，仅需少量训练图像即可实现有效模型训练。