# DAMSDet: Dynamic Adaptive Multispectral Detection Transformer with Competitive Query Selection and Adaptive Feature Fusion Source: [DAMSDet: Dynamic Adaptive Multispectral Detection Transformer with Competitive Query Selection and Adaptive Feature Fusion]() Collection index: [llms.txt]() Data updated: 2025-10-26T02:27:04.021Z Authors: Junjie Guo, Chenqiang Gao, Fangcen Liu, Deyu Meng, Xinbo Gao Published: 2024-03-01T07:03:27.000Z ## Abstract Infrared-visible object detection aims to achieve robust even full-day object detection by fusing the complementary information of infrared and visible images. However, highly dynamically variable complementary characteristics and commonly existing modality misalignment make the fusion of complementary information difficult. In this paper, we propose a Dynamic Adaptive Multispectral Detection Transformer (DAMSDet) to simultaneously address these two challenges. Specifically, we propose a Modality Competitive Query Selection strategy to provide useful prior information. This strategy can dynamically select basic salient modality feature representation for each object. To effectively mine the complementary information and adapt to misalignment situations, we propose a Multispectral Deformable Cross-attention module to adaptively sample and aggregate multi-semantic level features of infrared and visible images for each object. In addition, we further adopt the cascade structure of DETR to better mine complementary information. Experiments on four public datasets of different scenes demonstrate significant improvements compared to other state-of-the-art methods. The code will be released at https://github.com/gjj45/DAMSDet. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Object Detection on FLIR (test)](): Object Detection; FLIR (test); mAP50: 0.866. - [Object Detection on FLIR 5-shot (test)](): Object Detection; FLIR 5-shot (test); mAP50: 40.63. - [Object Detection on FLIR 10-shot (test)](): Object Detection; FLIR 10-shot (test); mAP50: 47.4. - [Object Detection on M3FD (Class-wise mAP50)](): Object Detection; M3FD; mAP50 Person: 18.15. - [Object Detection on M3FD](): Object Detection; M3FD; AP (Person): 23.25. - [Object Detection on M3FD (mAP, mAP50, mAP75)](): Object Detection; M3FD; mAP: 52.9. - [Object Detection on FLIR](): Object Detection; FLIR; mAP: 57.08. - [Object Detection on M3FD dataset](): Object Detection; M3FD dataset; mAP@0.5: 80.2. ## Original sources and implementation [Original paper]() [PDF]()