Automatic Aug-Aware Contrastive Proposal Encoding for Few-Shot Object Detection of Remote Sensing Images.
IEEE Trans. Geosci. Remote. Sens.(2023)
摘要
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.
更多查看译文
关键词
remote sensing,images,detection,aug-aware,few-shot
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要