Improving More Instance Segmentation and Better Object Detection in Remote Sensing Imagery Based on Cascade Mask R-CNN
Durga Kumar, Xiaoling Zhang
Abstract
In this paper, our approach is high-quality instance segmentation contains object detection in Remote Sensing imagery. In instance segmentation cross-entropy used as a loss function and intersection-over-union (IoU) used as a network performance measurement metric while in object detection, intersection over union (IoU) is often used to describe pos-itive/negative thresholds. Using IoU as a loss function can solve the problem between the loss function and the metric of the evaluation. We proposed a max-batch soft IoU training approach that eliminates the fixed IoU loss. randomness of the initial max-batch gradient descent (GD) technique. It resolves the IoU loss function's instability. However, our proposed method Cascade Mask R-CNN with max-batch soft IoU produces better results on the NWPU VHR-10 dataset for object detection and instance segmentation.