An Enhanced Light Object Detection for Indiscernible Object in the Special Scene
Quanyou Zhang, Yong Feng, Yongheng Wang, Zhejiang Lab, Yuhang district, Hangzhou, China, Baohua Qiang, Lufeng Wang, Zebin Zhang · Journal of Engineering Research · 2022
We present a transfer learning method named Special Application Transfer (SAT) for special object detection in a real life scenario. Our method improves fine-tuning hyper-parameter and adds unrecognized samples to detect special samples when training object detection neural networks for classification. We implement the model of NanoDet on special supervised datasets and fine-tune the hyper-parameter on a target task. More importantly, we combine a few carefully selected samples in training and simple heuristic fine-tuning to achieve good performance on special object detection in real-life scenarios. Our method (SAT) performs well across surprisingly the small dataset the medium dataset and the large dataset. SAT achieves 95% AP (Average Precision) on the small dataset, 94.8% AP on the medium dataset, and 94.5% AP on the large dataset. The performances of AP run-time and training convergence are perfect, compared with the original method and well-established famous methods on the challenging COCO dataset and our dataset. We hope our work could promote and complete the practical application in more real life scenarios.