Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2404.17360 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912642996633600 |
|---|---|
| author | Yuan, Maoxun Cui, Bo Zhao, Tianyi Wang, Jiayi Fu, Shan Yang, Xue Wei, Xingxing |
| author_facet | Yuan, Maoxun Cui, Bo Zhao, Tianyi Wang, Jiayi Fu, Shan Yang, Xue Wei, Xingxing |
| contents | Semantic analysis on visible (RGB) and infrared (IR) images has gained significant attention due to their enhanced accuracy and robustness under challenging conditions including low-illumination and adverse weather. However, due to the lack of pre-trained foundation models on the large-scale infrared image datasets, existing methods prefer to design task-specific frameworks and directly fine-tune them with pre-trained foundation models on their RGB-IR semantic relevance datasets, which results in poor scalability and limited generalization. To address these limitations, we propose UniRGB-IR, a scalable and efficient framework for RGB-IR semantic tasks that introduces a novel adapter mechanism to effectively incorporate rich multi-modal features into pre-trained RGB-based foundation models. Our framework comprises three key components: a vision transformer (ViT) foundation model, a Multi-modal Feature Pool (MFP) module, and a Supplementary Feature Injector (SFI) module. The MFP and SFI modules cooperate with each other as an adpater to effectively complement the ViT features with the contextual multi-scale features. During training process, we freeze the entire foundation model to inherit prior knowledge and only optimize the MFP and SFI modules. Furthermore, to verify the effectiveness of our framework, we utilize the ViT-Base as the pre-trained foundation model to perform extensive experiments. Experimental results on various RGB-IR semantic tasks demonstrate that our method can achieve state-of-the-art performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_17360 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | UniRGB-IR: A Unified Framework for Visible-Infrared Semantic Tasks via Adapter Tuning Yuan, Maoxun Cui, Bo Zhao, Tianyi Wang, Jiayi Fu, Shan Yang, Xue Wei, Xingxing Computer Vision and Pattern Recognition Semantic analysis on visible (RGB) and infrared (IR) images has gained significant attention due to their enhanced accuracy and robustness under challenging conditions including low-illumination and adverse weather. However, due to the lack of pre-trained foundation models on the large-scale infrared image datasets, existing methods prefer to design task-specific frameworks and directly fine-tune them with pre-trained foundation models on their RGB-IR semantic relevance datasets, which results in poor scalability and limited generalization. To address these limitations, we propose UniRGB-IR, a scalable and efficient framework for RGB-IR semantic tasks that introduces a novel adapter mechanism to effectively incorporate rich multi-modal features into pre-trained RGB-based foundation models. Our framework comprises three key components: a vision transformer (ViT) foundation model, a Multi-modal Feature Pool (MFP) module, and a Supplementary Feature Injector (SFI) module. The MFP and SFI modules cooperate with each other as an adpater to effectively complement the ViT features with the contextual multi-scale features. During training process, we freeze the entire foundation model to inherit prior knowledge and only optimize the MFP and SFI modules. Furthermore, to verify the effectiveness of our framework, we utilize the ViT-Base as the pre-trained foundation model to perform extensive experiments. Experimental results on various RGB-IR semantic tasks demonstrate that our method can achieve state-of-the-art performance. |
| title | UniRGB-IR: A Unified Framework for Visible-Infrared Semantic Tasks via Adapter Tuning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.17360 |