<scp>CFISRO</scp> : Cross‐Modal Feature Interaction and Similarity Ranking Optimization for Image‐Text Retrieval

ABSTRACT Image‐text retrieval faces challenges such as insufficient fusion of cross‐modal matching relationships, limited ability to distinguish between positive and negative samples, and inadequate feature representation. To address these issues, this paper proposes a new visual‐semantic interaction network (CFISRO). Building upon standard feature extractors, the network jointly models image and text features through a multi‐layer cross‐interaction module, capturing the rich semantic relationships between images and text. During the training process, a positive–negative sample similarity ranking optimization strategy is introduced to effectively reduce the distance between matching sample pairs while expanding the distance between non‐matching samples, enhancing the model's ability to distinguish. Furthermore, the network optimizes the image‐text matching classification performance by minimizing the difference between the predicted probability distribution and the true label distribution. Overall, CFISRO builds a collaborative optimization mechanism across multiple levels of image‐text representation learning, similarity modeling, and matching discrimination, significantly improving the representation quality and matching accuracy in cross‐modal retrieval tasks. Experimental results show that our method achieves excellent performance on benchmark datasets such as MS‐COCO and Flickr30K.