Pretrained visual-language models have made significant advancements in multimodal tasks, including image-text retrieval. However, a major challenge in image-text matching lies in language bias, where models predominantly rely on language priors and neglect to adequately consider the visual content. We thus present Multimodal ASsociation Score (MASS), a framework that reduces the reliance on language priors for better visual accuracy in image-text matching problems. It can be seamlessly incorporated into existing visual-language models without necessitating additional training. Our experiments have shown that MASS effectively lessens language bias without losing an understanding of linguistic compositionality. Overall, MASS offers a promising solution for enhancing image-text matching performance in visual-language models.
@article{arxiv.2501.11469,
title = {MASS: Overcoming Language Bias in Image-Text Matching},
author = {Jiwan Chung and Seungwon Lim and Sangkyu Lee and Youngjae Yu},
journal= {arXiv preprint arXiv:2501.11469},
year = {2025}
}