SCLNet: A Scale-Robust Complementary Learning Network for Object Detection in UAV Images

• Published in: IEEE transactions on geoscience and remote sensing Vol. 62; pp. 1 - 19
• Main Authors: Li, Xuexue, Diao, Wenhui, Mao, Yongqiang, Li, Xinming, Sun, Xian
• Format: Journal Article
• Language: English
• Published: New York IEEE 2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptation models; Autonomous aerial vehicles; Complement; Complementary learning; Computational modeling; Cooperation; Decoding; Detectors; Effectiveness; Feature extraction; Geoscience and remote sensing; Information processing; Learning; Object detection; Object recognition; Occlusion; Performance enhancement; Representations; Robustness; Robustness (mathematics); scale challenges; scale variation; Semantics; small objects; Training; Unmanned aerial vehicles

Most recent unmanned aerial vehicle (UAV) detectors focus primarily on general challenges such as uneven distribution and occlusion. However, the neglect of scale challenges, which encompass scale variation and small objects, continues to hinder object detection in UAV images. Although existing work...