MASS: Overcoming Language Bias in Image-Text Matching
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929683016187904 |
|---|---|
| author | Chung, Jiwan Lim, Seungwon Lee, Sangkyu Yu, Youngjae |
| author_facet | Chung, Jiwan Lim, Seungwon Lee, Sangkyu Yu, Youngjae |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_11469 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MASS: Overcoming Language Bias in Image-Text Matching Chung, Jiwan Lim, Seungwon Lee, Sangkyu Yu, Youngjae Computer Vision and Pattern Recognition Machine Learning 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. |
| title | MASS: Overcoming Language Bias in Image-Text Matching |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2501.11469 |