Zero-Shot Aerial Object Detection with Visual Description Regularization

arXiv:2402.18233v1 Announce Type: new
Abstract: Existing object detection models are mainly trained on large-scale labeled datasets. However, annotating data for novel aerial object classes is expensive since it is time-consuming and may require expert knowledge. Thus, it is desirable to study label-efficient object detection methods on aerial images. In this work, we propose a zero-shot method for aerial object detection named visual Description Regularization, or DescReg. Concretely, we identify the weak semantic-visual correlation of the aerial objects and aim to …

abstract aerial arxiv cs.cv data datasets detection detection methods expert images knowledge novel regularization scale study type visual work zero-shot