Search papers, labs, and topics across Lattice.
This paper introduces LOGOS, a transformer-based framework that enhances oriented object detection in aerial imagery by utilizing textual prompts to modulate content queries dynamically. The method addresses key challenges such as angular discontinuity and inefficiencies in handling cluttered scenes, leading to improved accuracy in detecting densely packed and rotated objects. Extensive experiments on the DOTA dataset show that LOGOS surpasses existing state-of-the-art techniques, marking a significant advancement in the robustness and scalability of object detection in remote sensing applications.
Textual prompts can revolutionize object detection in aerial imagery, enabling models to adaptively focus on complex scenes with unprecedented accuracy.
Object detection in geospatial scenes, such as satellite and aerial imagery, poses significant challenges due to the varying orientations and densities of objects, as well as the complex backgrounds inherent to remote sensing imagery. Traditional methods for oriented object detection have struggled to address issues such as angular discontinuity, fixed query sizes, and inefficiencies in handling sparse or cluttered scenes. In this paper, we propose LOGOS, a novel transformer-based approach that leverages textual prompts to guide the detection of oriented objects in aerial scenes. In particular, our proposed approach incorporates prompt-modulated content queries to dynamically adjust the model's focus based on the provided text, thereby improving object detection accuracy in complex environments. Empirically, extensive experiments on the DOTA dataset demonstrate that LOGOS outperforms existing state-of-the-art methods, particularly in densely packed and rotated object scenarios. Our approach offers a significant step forward in improving the robustness and scalability of oriented object detection in remote sensing applications.
