UniRGB-IR: A Unified Framework for Visible-Infrared Downstream Tasks via Adapter Tuning

arXiv:2404.17360v1 Announce Type: new
Abstract: Semantic analysis on visible (RGB) and infrared (IR) images has gained attention for its ability to be more accurate and robust under low-illumination and complex weather conditions. 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. In this work, we propose …

adapter arxiv cs.cv framework tasks type via