SRDF: Single-Stage Rotate Object Detector via Dense Prediction and False Positive Suppression.

Oriented object detection has made astonishing progress. However, existing methods neglect to address the issue of false positives caused by the background or nearby clutter objects. Meanwhile, class imbalance and boundary overflow issues caused by the predicting rotation angles may affect the accuracy of rotated bounding box predictions. To address the above issues, we propose a single-stage rotate object detector via dense prediction and false positive suppression (SRDF). Specifically, we design an instance-level false positive suppression module (IFPSM), IFPSM acquires the weight information of target and nontarget regions by supervised learning of spatial feature encoding, and applies these weight values to the deep feature map, thereby attenuating the response signals of nontarget regions within the deep feature map. Compared to commonly used attention mechanisms, this approach more accurately suppresses false-positive regions. Then, we introduce a hybrid classification and regression method to represent the object orientation, the proposed method divide the angle into two segments for prediction, reducing the number of categories and narrowing the range of regression. This alleviates the issue of class imbalance caused by treating one degree as a single category in classification prediction, as well as the problem of boundary overflow caused by directly regressing the angle. In addition, we transform the traditional post-processing steps based on matching and searching to a 2-D probability distribution mathematical model, which accurately and quickly extracts the bounding boxes from dense prediction results. Extensive experiments on Remote Sensing, synthetic aperture radar (SAR), and Scene Text benchmarks demonstrate the superiority of the proposed SRDF method over state-of-the-art (SOTA) rotated object detection methods. Our codes are available at https://github.com/TomZandJerryZ/SRDF.