YOLOv3 Object Detection Model Based on MAML Algorithm
-
摘要: 作为典型的一体化卷积神经网络，YOLOv3模型的网路传输途径简单，检测速度相对较快，但检测精度较低。当遇到新的目标在训练数据集中存在的样本较少时，模型检测会更加不准确，甚至会出现检测不到的情况。本文基于与模型不相关的元学习算法（MAML）改进了YOLOv3主干网络的结构，使其具有内循环和外循环的梯度下降，在初始参数基础上进行多步的梯度调整，达到仅用小样本数据就能快速收敛的目的。实验结果表明，该方法使得YOLOv3模型的检测精度提升了5.24%，且可以使梯度下降保持稳定，有效地满足YOLOv3模型在小样本数据训练情况下识别目标位置的精准性和泛化性。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 about 5%. 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.
-
Key words:
- computer vision /
- image recognition /
- feature extraction /
- object detection /
- few shot learning
-
图 7 解冻网络层训练的损失函数曲线变化
Figure 7. Change curves of training loss of thawing network layer
表 1 分类结果的精确度比较结果
Table 1. Accuracy of classification results
Model Percision/% mAP/% YOLOv3 50.7 74.81 YOLOv3 with MAML 56.6 80.05 
下载: 导出CSV
-
[1] FAN Q, ZHUO W, TANG C K, et al. Few-shot object detection with attention-RPN and multi-relation detector[C]//2020 IEEE Conference on Computer Vision and Pattern Recognition. USA: IEEE, 2020: 4012-4021. [2] WANG T, ZHANG X P, YUAN L, et al. Few-shot adaptive faster R-CNN[C]//2019 IEEE Conference on Computer Vision and Pattern Recognition. USA: IEEE, 2019: 7166-7175. [3] 王鹏, 陆振宇, 詹天明, 等. 基于PDSSD改进型神经网络的小目标检测算法[J]. 计算机应用与软件, 2021, 38(1): 149-191. [4] FINN C, ABBEEL P, LEVINE S. Model-agnostic meta-learning for fast adaptation of deep networks[C]//Proceedings of the 34th International Conference on Machine Learning. USA: ACM, 2017: 1126-1135. [5] 李雅倩, 盖成远, 肖存军, 等. 基于细化多尺度深度特征的目标检测网络[J]. 电子学报, 2020, 48(12): 2360-2366. [6] REDMON J, FARHADI A. YOLOv3: An incremental improvement[EB/OL]. arXiv. org, (2018-04-08)[2019-04-01]. https://arXiv.org/abs/1804.02767. [7] BOCHKOVSKIY A, WANG C Y, LIAO H Y. YOLOv4: Optimal speed and accuracy of object detection[EB/OL]. arXiv. org, (2020-04-23)[2020-09-16]. https://arxiv.org/abs/2004.10934. [8] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//2014 IEEE Conference on Computer Vision and Pattern Recognition. USA: IEEE, 2014: 580-587. [9] HE K M, ZHANG X Y, REN S Q, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1904-1916. doi: 10.1109/TPAMI.2015.2389824 [10] GIRSHICK R. Fast R-CNN[C]//2015 IEEE International Conference on Computer Vision. Chile: IEEE, 2015: 1440-1448. [11] REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks[C]//2015 International Conference on Neural Information Processing Systems. [s.l.]:[s.n.], 2015: 91-99. [12] LIN T, DOLLÁR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]//2017 IEEE International Conference on Computer Vision. USA: IEEE, 2017: 2117-2125. [13] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: Unified, real-time object detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. USA: IEEE, 2016: 779-788. [14] LIU W, ANGUELOV D, ERHAN D, et al. SSD: Single shot multibox detector[C]//European Conference on Computer Vision. Cham: Springer, 2016: 21-37. [15] LIN T, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]//2017 International Conference on Computer Vision. Italy: IEEE, 2017: 2980-2988. [16] TIAN Z, SHEN C H, CHEN H, et al. FCOS: Fully convolutionalone-stage object detection[C]//2019 IEEE International Conference on Computer Vision. Korea: IEEE, 2019: 9626-9635. [17] 马振伟, 何高奇, 袁玉波. 基于小样本深度学习的通风柜橱窗状态识别方法[J]. 华东理工大学学报(自然科学版), 2020, 46(3): 428-435. [18] REDMON J, FARHADI A. YOLO9000: Better, faster, stronger[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. USA: IEEE, 2017: 7263-7271. -
点击查看大图
图(8) / 表(1)
计量
- 文章访问数: 485
- HTML全文浏览量: 216
- PDF下载量: 32
- 被引次数: 0
