Image Captioning for state-of-the-art VLMs has significantly improved over time; however, this comes at the cost of increased computational complexity, making them less accessible for resource-constrained applications such as mobile devices and assistive technologies. Alternatively, comparably smaller VLMs prioritize high-level scene descriptions, overlooking finer details that contribute to a richer understanding of an image. In this paper, we introduce a training-free framework that enhances caption diversity and informativeness by explicitly attending to distinct image regions using a comparably small VLM, BLIP, as the backbone. Our approach leverages structured segmentation to produce hierarchical representations that capture both global and localized semantics. Without requiring additional model training, we demonstrate that our method allows smaller VLMs to achieve performance comparable to larger models in terms of image-caption alignment, semantic integrity, and diversity. We evaluate our framework on MSCOCO, Flickr30k, and Nocaps test datasets, achieving a Div-2 score of 0.735, 0.750, and 0.748 for each dataset, respectively, while maintaining strong image-caption relevancy and semantic integrity with the human-annotated captions.

翻译：最先进的视觉语言模型（VLM）在图像描述生成方面已取得显著进展，但这是以计算复杂度增加为代价的，使其在移动设备和辅助技术等资源受限的应用中可及性降低。相比之下，相对较小的VLM优先考虑高层场景描述，忽略了有助于更丰富理解图像的细节。本文提出一种无需训练的框架，通过使用相对较小的VLM（BLIP）作为骨干网络，显式关注不同图像区域，从而增强描述的多样性和信息量。我们的方法利用结构化分割生成分层表示，以捕捉全局和局部语义。无需额外模型训练，我们证明该方法能使较小VLM在图像-描述对齐度、语义完整性和多样性方面达到与较大模型相当的性能。我们在MSCOCO、Flickr30k和Nocaps测试数据集上评估了该框架，分别实现了0.735、0.750和0.748的Div-2分数，同时保持了与人工标注描述之间较强的图像-描述相关性和语义完整性。