Image-text retrieval is one of the major tasks of cross-modal retrieval. Several approaches for this task map images and texts into a common space to create correspondences between the two modalities. However, due to the content (semantics) richness of an image, redundant secondary information in an image may cause false matches. To address this issue, this paper presents a semantic optimization approach, implemented as a Visual Semantic Loss (VSL), to assist the model in focusing on an image's main content. This approach is inspired by how people typically annotate the content of an image by describing its main content. Thus, we leverage the annotated texts corresponding to an image to assist the model in capturing the main content of the image, reducing the negative impact of secondary content. Extensive experiments on two benchmark datasets (MSCOCO and Flickr30K) demonstrate the superior performance of our method. The code is available at: https://github.com/ZhangXu0963/VSL.

翻译：图像-文本检索是跨模态检索的主要任务之一。针对该任务，现有方法将图像和文本映射到公共空间以建立两种模态之间的对应关系。然而，由于图像内容（语义）的丰富性，图像中冗余的次要信息可能导致错误匹配。为解决这一问题，本文提出了一种语义优化方法，通过实现视觉语义损失（Visual Semantic Loss, VSL）来帮助模型聚焦于图像的主要内容。该方法的灵感来源于人类通常通过描述图像主要内容来标注图像内容的方式。因此，我们利用与图像对应的标注文本，协助模型捕捉图像的主要语义，减少次要内容的负面影响。在两个基准数据集（MSCOCO和Flickr30K）上的大量实验表明，我们方法具有优越性能。代码已开源：https://github.com/ZhangXu0963/VSL。