Data Augmentation For Small Object using Fast AutoAugment
This addresses a challenging and important issue in object detection for computer vision applications, but it is incremental as it builds on existing Fast AutoAugment techniques.
The paper tackled the problem of poor detection performance for small objects in computer vision by proposing an optimal data augmentation method using Fast AutoAugment, resulting in a 20% performance improvement on the DOTA dataset.
In recent years, there has been tremendous progress in object detection performance. However, despite these advances, the detection performance for small objects is significantly inferior to that of large objects. Detecting small objects is one of the most challenging and important problems in computer vision. To improve the detection performance for small objects, we propose an optimal data augmentation method using Fast AutoAugment. Through our proposed method, we can quickly find optimal augmentation policies that can overcome degradation when detecting small objects, and we achieve a 20% performance improvement on the DOTA dataset.