Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2510.13131 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912648297185280 |
|---|---|
| author | Chen, Rongjun Yao, Chengsi Ren, Jinchang Zeng, Xianxian Wang, Peixian Yuan, Jun Li, Jiawen Zhao, Huimin Lu, Xu |
| author_facet | Chen, Rongjun Yao, Chengsi Ren, Jinchang Zeng, Xianxian Wang, Peixian Yuan, Jun Li, Jiawen Zhao, Huimin Lu, Xu |
| contents | Text-image alignment constitutes a foundational challenge in multimedia content understanding, where effective modeling of cross-modal semantic correspondences critically enhances retrieval system performance through joint embedding space optimization. Given the inherent difference in information entropy between texts and images, conventional approaches often show an imbalance in the mutual retrieval of these two modalities. To address this particular challenge, we propose to use the open semantic knowledge of Large Language Model (LLM) to fill for the entropy gap and reproduce the alignment ability of humans in these tasks. Our entropy-enhancing alignment is achieved through a two-step process: 1) a new prompt template that does not rely on explicit knowledge in the task domain is designed to use LLM to enhance the polysemy description of the text modality. By analogy, the information entropy of the text modality relative to the visual modality is increased; 2) A hypergraph adapter is used to construct multilateral connections between the text and image modalities, which can correct the positive and negative matching errors for synonymous semantics in the same fixed embedding space, whilst reducing the noise caused by open semantic entropy by mapping the reduced dimensions back to the original dimensions. Comprehensive evaluations on the Flickr30K and MS-COCO benchmarks validate the superiority of our Open Semantic Hypergraph Adapter (OS-HGAdapter), showcasing 16.8\% (text-to-image) and 40.1\% (image-to-text) cross-modal retrieval gains over existing methods while establishing new state-of-the-art performance in semantic alignment tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_13131 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | OS-HGAdapter: Open Semantic Hypergraph Adapter for Large Language Models Assisted Entropy-Enhanced Image-Text Alignment Chen, Rongjun Yao, Chengsi Ren, Jinchang Zeng, Xianxian Wang, Peixian Yuan, Jun Li, Jiawen Zhao, Huimin Lu, Xu Computer Vision and Pattern Recognition Multimedia Text-image alignment constitutes a foundational challenge in multimedia content understanding, where effective modeling of cross-modal semantic correspondences critically enhances retrieval system performance through joint embedding space optimization. Given the inherent difference in information entropy between texts and images, conventional approaches often show an imbalance in the mutual retrieval of these two modalities. To address this particular challenge, we propose to use the open semantic knowledge of Large Language Model (LLM) to fill for the entropy gap and reproduce the alignment ability of humans in these tasks. Our entropy-enhancing alignment is achieved through a two-step process: 1) a new prompt template that does not rely on explicit knowledge in the task domain is designed to use LLM to enhance the polysemy description of the text modality. By analogy, the information entropy of the text modality relative to the visual modality is increased; 2) A hypergraph adapter is used to construct multilateral connections between the text and image modalities, which can correct the positive and negative matching errors for synonymous semantics in the same fixed embedding space, whilst reducing the noise caused by open semantic entropy by mapping the reduced dimensions back to the original dimensions. Comprehensive evaluations on the Flickr30K and MS-COCO benchmarks validate the superiority of our Open Semantic Hypergraph Adapter (OS-HGAdapter), showcasing 16.8\% (text-to-image) and 40.1\% (image-to-text) cross-modal retrieval gains over existing methods while establishing new state-of-the-art performance in semantic alignment tasks. |
| title | OS-HGAdapter: Open Semantic Hypergraph Adapter for Large Language Models Assisted Entropy-Enhanced Image-Text Alignment |
| topic | Computer Vision and Pattern Recognition Multimedia |
| url | https://arxiv.org/abs/2510.13131 |