Unsupervised data augmentation for object detection
This addresses a bottleneck in object detection for scenarios with limited labeled data, though it appears incremental as it builds on existing methods like YOLOv4 and GANs.
The paper tackles the problem of data augmentation for object detection when labeled bounding boxes are unavailable by proposing a GAN-based framework that generates images with known object positions, enabling the creation of labeled training data.
Data augmentation has always been an effective way to overcome overfitting issue when the dataset is small. There are already lots of augmentation operations such as horizontal flip, random crop or even Mixup. However, unlike image classification task, we cannot simply perform these operations for object detection task because of the lack of labeled bounding boxes information for corresponding generated images. To address this challenge, we propose a framework making use of Generative Adversarial Networks(GAN) to perform unsupervised data augmentation. To be specific, based on the recently supreme performance of YOLOv4, we propose a two-step pipeline that enables us to generate an image where the object lies in a certain position. In this way, we can accomplish the goal that generating an image with bounding box label.