SFDN: A Novel Semantic Feature Decouple Network for Fine-Grained Remote Sensing Object Detection (opens in new tab)

Fine-grained object detection (FGOD) aims to identify subcategories of objects by extracting more discriminative semantic information. Bounding box regression typically requires detailed texture and edge information to accurately delineate object boundaries, while classification requires richer semantic information. However, existing methods use the same input features in the model, resulting in an imbalance between the localization task and the fine-grained classification task. To address th...