NBBOX: Noisy Bounding Box Improves Remote Sensing Object Detection
This addresses the challenge of inconsistent bounding box annotations in aerial imagery for remote sensing applications, offering an incremental but practical enhancement to data augmentation strategies.
The paper tackles the problem of limited data in remote sensing object detection by proposing NBBOX, a data augmentation technique that applies noise to bounding boxes instead of images, and it shows significant improvements in detection performance on DOTA and DIOR-R datasets while being more time-efficient than other methods.
Data augmentation has shown significant advancements in computer vision to improve model performance over the years, particularly in scenarios with limited and insufficient data. Currently, most studies focus on adjusting the image or its features to expand the size, quality, and variety of samples during training in various tasks including object detection. However, we argue that it is necessary to investigate bounding box transformations as a data augmentation technique rather than image-level transformations, especially in aerial imagery due to potentially inconsistent bounding box annotations. Hence, this letter presents a thorough investigation of bounding box transformation in terms of scaling, rotation, and translation for remote sensing object detection. We call this augmentation strategy NBBOX (Noise Injection into Bounding Box). We conduct extensive experiments on DOTA and DIOR-R, both well-known datasets that include a variety of rotated generic objects in aerial images. Experimental results show that our approach significantly improves remote sensing object detection without whistles and bells and it is more time-efficient than other state-of-the-art augmentation strategies.