Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2412.16869 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929644452708352 |
|---|---|
| author | Wang, Yeyuan Gao, Dehong Li, Bin Long, Rujiao Yi, Lei Cai, Xiaoyan Yang, Libin Zhang, Jinxia Yu, Shanqing Xuan, Qi |
| author_facet | Wang, Yeyuan Gao, Dehong Li, Bin Long, Rujiao Yi, Lei Cai, Xiaoyan Yang, Libin Zhang, Jinxia Yu, Shanqing Xuan, Qi |
| contents | The impressive performance of Large Language Model (LLM) has prompted researchers to develop Multi-modal LLM (MLLM), which has shown great potential for various multi-modal tasks. However, current MLLM often struggles to effectively address fine-grained multi-modal challenges. We argue that this limitation is closely linked to the models' visual grounding capabilities. The restricted spatial awareness and perceptual acuity of visual encoders frequently lead to interference from irrelevant background information in images, causing the models to overlook subtle but crucial details. As a result, achieving fine-grained regional visual comprehension becomes difficult. In this paper, we break down multi-modal understanding into two stages, from Coarse to Fine (CoF). In the first stage, we prompt the MLLM to locate the approximate area of the answer. In the second stage, we further enhance the model's focus on relevant areas within the image through visual prompt engineering, adjusting attention weights of pertinent regions. This, in turn, improves both visual grounding and overall performance in downstream tasks. Our experiments show that this approach significantly boosts the performance of baseline models, demonstrating notable generalization and effectiveness. Our CoF approach is available online at https://github.com/Gavin001201/CoF. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_16869 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CoF: Coarse to Fine-Grained Image Understanding for Multi-modal Large Language Models Wang, Yeyuan Gao, Dehong Li, Bin Long, Rujiao Yi, Lei Cai, Xiaoyan Yang, Libin Zhang, Jinxia Yu, Shanqing Xuan, Qi Computer Vision and Pattern Recognition The impressive performance of Large Language Model (LLM) has prompted researchers to develop Multi-modal LLM (MLLM), which has shown great potential for various multi-modal tasks. However, current MLLM often struggles to effectively address fine-grained multi-modal challenges. We argue that this limitation is closely linked to the models' visual grounding capabilities. The restricted spatial awareness and perceptual acuity of visual encoders frequently lead to interference from irrelevant background information in images, causing the models to overlook subtle but crucial details. As a result, achieving fine-grained regional visual comprehension becomes difficult. In this paper, we break down multi-modal understanding into two stages, from Coarse to Fine (CoF). In the first stage, we prompt the MLLM to locate the approximate area of the answer. In the second stage, we further enhance the model's focus on relevant areas within the image through visual prompt engineering, adjusting attention weights of pertinent regions. This, in turn, improves both visual grounding and overall performance in downstream tasks. Our experiments show that this approach significantly boosts the performance of baseline models, demonstrating notable generalization and effectiveness. Our CoF approach is available online at https://github.com/Gavin001201/CoF. |
| title | CoF: Coarse to Fine-Grained Image Understanding for Multi-modal Large Language Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.16869 |