Wholly-WOOD: Wholly Leveraging Diversified-quality Labels for Weakly-supervised Oriented Object Detection

TL;DR

Wholly-WOOD is a weakly-supervised oriented object detection framework that effectively utilizes various weak labels like points and horizontal boxes, achieving near RBox-level performance with less annotation effort.

Contribution

It introduces a unified framework that leverages diverse weak labels for oriented object detection, reducing reliance on costly rotation annotations.

Findings

Achieves near RBox-trained performance using only HBoxes.

Effectively utilizes weak labels like points and HBoxes.

Reduces annotation effort significantly.

Abstract

Accurately estimating the orientation of visual objects with compact rotated bounding boxes (RBoxes) has become a prominent demand, which challenges existing object detection paradigms that only use horizontal bounding boxes (HBoxes). To equip the detectors with orientation awareness, supervised regression/classification modules have been introduced at the high cost of rotation annotation. Meanwhile, some existing datasets with oriented objects are already annotated with horizontal boxes or even single points. It becomes attractive yet remains open for effectively utilizing weaker single point and horizontal annotations to train an oriented object detector (OOD). We develop Wholly-WOOD, a weakly-supervised OOD framework, capable of wholly leveraging various labeling forms (Points, HBoxes, RBoxes, and their combination) in a unified fashion. By only using HBox for training, our Wholly-WOOD achieves performance very close to that of the RBox-trained counterpart on remote sensing and other areas, significantly reducing the tedious efforts on labor-intensive annotation for oriented objects. The source codes are available at https://github.com/VisionXLab/whollywood (PyTorch-based) and https://github.com/VisionXLab/whollywood-jittor (Jittor-based).