Abstract:
In the annotation of remote sensing images (RSIs), the effectiveness of common object detection methods trained on only a few samples decreases instantly, which has promp...Show MoreMetadata
Abstract:
In the annotation of remote sensing images (RSIs), the effectiveness of common object detection methods trained on only a few samples decreases instantly, which has prompted increasing research on the few-shot problem in remote sensing. RSIs often exhibit suboptimal performance in few-shot scenarios due to the intricate nature of scene information interference and the high degree of cosine similarity, both of which present significant challenges to their effectiveness. In this article, a two-stage detection framework based on fine-tuning is selected to deal with the common problems in the few-shot task of the remote sensing domain. Considering the excessive scale variation in instances in the remote sensing datasets, we introduce an automatically learned aug-aware search module to provide an intelligent data augmentation solution for Faster R-CNN using different optimal augmentation policies searched by the network to fit the current dataset. We introduce a contrastive RoI branch to better classify novel class proposal features that are easily confused by the base class. We named our work augmentation-aware contrastive proposal encoding (AACE) and conducted extensive experiments on two common object detection datasets in remote sensing, NWPU VHR 10 and DIOR, on which AACE achieved about 2.30% and 2.61% improvement, respectively, in the number of shots listed in the article, compared with other algorithms.
Published in: IEEE Transactions on Geoscience and Remote Sensing ( Volume: 61)