Few training data for Objection Detection
Baoxiang Jiang, Jingbo Xia, Shiyan Li · Proceedings of the 2020 4th International Conference on Electronic Information Technology and Computer Engineering · 2020
Deep learning method of object detection has achieved excellent results, but most of the object detection network training processes are supervised learning. The performance improvement is driven by a large amount of annotation data to drive deeper and more complex network structures. For object detection tasks, it takes 7-42 seconds to complete the precise labeling of a single target rectangle. As the complexity of the scene and the density of objects increase, the cost of labeling becomes higher. In this paper, we propose a semi-supervised object detection framework based on self-training to solve the problem of few training data object detection. We have improved the method of self-training to generate pseudo-labels for object detection tasks, pseudo-labels made by using automatic threshold search and multi-view detection. This method uses semi-supervised learning to mine and utilize unlabeled data, as well as the use of data augmentation methods to enhance the generalization of labeled data. It can achieve high accuracy in object detection models trained with few training data. We proposed several experiments on two publicly available datasets with few training data, and experiments demon-state that our methods based on semi-supervised learning are better than that based on supervised learning.