The traditional object detection algorithm is subject to changeable environment, complex background, target aggregation and too many small targets, showing disadvantages in the detection of aerial remote sensing images. This study presents the Attention-GAN-Mask R-CNN model for the object detection in remote sensing image based on attention mechanism and generative adversarial network (GAN). This model combines attention, generative adversarial network and Mask R-CNN to solve the above problems. The experimental results show that this method can improve the efficiency and accuracy of target detection in the complex remote sensing images.