Delving Into Coarse-Fine Feature Interaction Alignment for UAV Object Detection

Yanchao Bi, Yang Ning, Xiushan Nie

Abstract: Due to limited features and dense object layouts, object detection in UAV images is challenging. Given that existing feature fusion methods have not fully explored the relationship between fine- and coarse-grained features, direct feature fusion can result in poor correlation between them, hindering the representative capability of fine-grained semantic information. To alleviate this issue, we introduce a method of Coarse-fine Feature Interaction Alignment (CFIA), which enhances the correlation between coarse-grained and fine-grained features across multiscale feature maps through their interactive alignment. Firstly, we present the Wavelet-based High-frequency Preserving Downsampling (WHPD), utilizing wavelet transform to extract highfrequency information to enhance object boundaries, minimizing crucial fine-grained information loss. Secondly, we propose the Feature Refinement and Interaction Alignment Strategy (FRIAS), which achieves feature interaction alignment by establishing the association of feature maps between coarse-grained and finegrained features. This enhances the representative capability of feature maps at various scales for detecting small objects. Extensive experiments on the VisDrone, CARPK, and Drone-vs-Bird datasets have demonstrated the effectiveness of the CFIA method, which is highly competitive with state-of-the-art methods. The code is available at https://github.com/b-yanchao/CFIA.git.