Abstract:
Object detection has been a research hotspot in the field of computer vision in recent years. Due to the extensive application of deep learning, the target detection technology combined with deep learning has been developing and making continuous breakthroughs. In the field of target detection, it is difficult to solve the problem of target detection with few sample categories, and detect small targets with high accuracy via the training with few sample categories. By means of the model-agnostic meta-learning (MAML) algorithm in meta learning, this paper improves the information transmission form of the backbone network in YOLOv3 to make Darknet-53 achieve two stages of parameter internal update and external update in gradient descent. By multi-step gradient adjustment on the initial parameters, the trained weights can focus more on the feature information of the target. Even only via a small number of sample categories, it can also maintain the sensitivity to the target in the new task. It is shown via the experiment results that the mean average precision(mAP) value of YOLOv3 model attains 74.81%, and the mAP value of YOLOv3 model based on MAML algorithm can reach 80.05%, which improves the accuracy by 5.24%. The network structure and training mechanism of the modified YOLOv3 via MAML can improve the accuracy of detection in training and prediction, and the trained weights can make the model have high detection accuracy and high generalization.