IPS-YOLO: Iterative Pseudo-Fully Supervised Training of YOLO for Weakly Supervised Object Detection in Remote Sensing Images

Weakly supervised object detection (WSOD) in remote sensing images (RSIs) only requires image-level labels, greatly reducing the cost of manual annotations. Recently, the pseudo-fully supervised object detection (pseudo-FSOD) models give better performance than traditional WSOD models based on multiple instance learning. However, the existing pseudo-FSOD models still have two problems that need to be addressed. First, existing models tend to focus on the salient parts of object rather than the whole object. Second, the pseudo ground truth (PGT) cannot be continuously improved during the training process. For the first problem, a filtering and weighted synthesis guided by category confidence score (FWSC) strategy is proposed to generate PGT. The FWSC strategy first removes the instances with low category confidence score (CCS), then, to cover the whole object as much as possible, any two instances are weighted and synthesized according to their CCSs if they have very high spatial overlap, otherwise, the nonmaximum suppression (NMS) operation is conducted. For the second problem, an iterative refinement (IR) scheme of PGT is proposed. Specifically, the PGT instances produced by the FWSC strategy are first used to train a YOLO model, then a filtering and weighted synthesis guided by IoU (FWSI) strategy employs the detection results inferred from the trained YOLO model to refine the PGT instances, and the above two steps can be repeated multiple times. Furthermore, three improvement strategies are proposed to enhance the traditional baseline WSOD model in proposals generation, the selection of augmented samples, and the definition of pseudo labels, respectively. The ablation studies demonstrate the effectiveness of FWSC strategy, IR scheme of PGT, and the three improvement strategies of baseline model. The comparisons with popular WSOD models show that our model gives the best results on the NWPU VHR-10.v2 and DIOR datasets.