ImageRef-VL: Enabling Contextual Image Referencing in Vision-Language Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909463157407744 |
|---|---|
| author | Yi, Jingwei Yin, Junhao Xu, Ju Bao, Peng Wang, Yongliang Fan, Wei Wang, Hao |
| author_facet | Yi, Jingwei Yin, Junhao Xu, Ju Bao, Peng Wang, Yongliang Fan, Wei Wang, Hao |
| contents | Vision-Language Models (VLMs) have demonstrated remarkable capabilities in understanding multimodal inputs and have been widely integrated into Retrieval-Augmented Generation (RAG) based conversational systems. While current VLM-powered chatbots can provide textual source references in their responses, they exhibit significant limitations in referencing contextually relevant images during conversations. In this paper, we introduce Contextual Image Reference -- the ability to appropriately reference relevant images from retrieval documents based on conversation context -- and systematically investigate VLMs' capability in this aspect. We conduct the first evaluation for contextual image referencing, comprising a dedicated testing dataset and evaluation metrics. Furthermore, we propose ImageRef-VL, a method that significantly enhances open-source VLMs' image referencing capabilities through instruction fine-tuning on a large-scale, manually curated multimodal conversation dataset. Experimental results demonstrate that ImageRef-VL not only outperforms proprietary models but also achieves an 88% performance improvement over state-of-the-art open-source VLMs in contextual image referencing tasks. Our code is available at https://github.com/bytedance/ImageRef-VL. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_12418 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ImageRef-VL: Enabling Contextual Image Referencing in Vision-Language Models Yi, Jingwei Yin, Junhao Xu, Ju Bao, Peng Wang, Yongliang Fan, Wei Wang, Hao Computer Vision and Pattern Recognition Artificial Intelligence Vision-Language Models (VLMs) have demonstrated remarkable capabilities in understanding multimodal inputs and have been widely integrated into Retrieval-Augmented Generation (RAG) based conversational systems. While current VLM-powered chatbots can provide textual source references in their responses, they exhibit significant limitations in referencing contextually relevant images during conversations. In this paper, we introduce Contextual Image Reference -- the ability to appropriately reference relevant images from retrieval documents based on conversation context -- and systematically investigate VLMs' capability in this aspect. We conduct the first evaluation for contextual image referencing, comprising a dedicated testing dataset and evaluation metrics. Furthermore, we propose ImageRef-VL, a method that significantly enhances open-source VLMs' image referencing capabilities through instruction fine-tuning on a large-scale, manually curated multimodal conversation dataset. Experimental results demonstrate that ImageRef-VL not only outperforms proprietary models but also achieves an 88% performance improvement over state-of-the-art open-source VLMs in contextual image referencing tasks. Our code is available at https://github.com/bytedance/ImageRef-VL. |
| title | ImageRef-VL: Enabling Contextual Image Referencing in Vision-Language Models |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2501.12418 |