This paper proposes a transfer learning method for an object detection model using a genetic algorithm to solve the difficulty of the conventional transfer learning of deep learning-based object detection models. The genetic algorithm of the proposed method can select the re-learning layers automatically in the transfer learning process instead of a trial-and-error selection of the conventional method. Transfer learning was performed using the EfficientDet-d0 model pre-trained on the COCO dataset and the Global Wheat Head Detection (GWHD) dataset, and experiments were conducted to compare fine-tuning and the proposed method. Using the training data and the validation data of the GWHD, we compare the mean average precision (mAP) of the models trained by the conventional and the proposed methods, respectively, on the test data of the GWHD. It is confirmed that the model trained by the proposed method has higher performance than the model trained by the conventional method. The average of mAP of the proposed method, which automatically selects the re-learning layer (≈0.603), is higher than the average of mAP of the conventional method (≈0.594). Furthermore, the standard deviation of results obtained by the proposed method is smaller than that of the conventional method, and it shows the stable learning process of the proposed method.

1. [1] Z. Zou, Z. Shi, Y. Guo, and J. Ye, “Object detection in 20 years: A survey,” arXiv:1905.05055, 2019.
2. [2] W. Liu, S. Chen, and L. Wei, “Improving Street Object Detection Using Transfer Learning: From Generic Model to Specific Model,” J. Adv. Comput. Intell. Intell. Inform., Vol.22, No.6, pp. 869-874, 2018.
3. [3] J. Liu, “Tomato Yield Estimation Based on Object Detection,” J. Adv. Comput. Intell. Intell. Inform., Vol.22, No.7, pp. 1120-1125, 2018.
4. [4] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks,” F. Pereira, C. J. C. Burges, L. Bottou, and K. Q. Weinberger (Eds.), Advances in Neural Information Processing Systems 25 (NIPS), pp. 1097-1105, 2012.
5. [5] L. Jiao, F. Zhang, F. Liu, S. Yang, L. Li, Z. Feng, and R. Qu, “A Survey of Deep Learning-Based Object Detection,” IEEE Access, Vol.7, pp. 128837-128868, 2019.
6. [6] S. J. Pan and Q. Yang, “A Survey on Transfer Learning,” IEEE Trans. on Knowledge and Data Engineering, Vol.22, No.10, pp. 1345-1359, 2010.
7. [7] Y. Sawada and K. Kozuka, “Whole layers transfer learning of deep neural networks for a small scale dataset,” Int. J. of Machine Learning and Computing, Vol.6, No.1, pp. 27-31, 2016.
8. [8] H. Zunair, N. Mohammed, and S. Momen, “Unconventional Wisdom: A New Transfer Learning Approach Applied to Bengali Numeral Classification,” Int. Conf. on Bangla Speech and Language Processing (ICBSLP), 2018.
9. [9] S. Imai and H. Nobuhara, “Stepwise PathNet: Transfer Learning Algorithm to Improve Network Structure Versatility,” IEEE Int. Conf. on Systems, Man, and Cybernetics (SMC), pp. 918-922, 2018.
10. [10] A. M. Thengade and R. Dondal, “Genetic algorithm–survey paper,” MPGI National Multi Conf. (MPGINMC), pp. 25-29, 2012.
11. [11] S. Nagae, S. Kawai, and H. Nobuhara, “Transfer Learning Layer Selection Using Genetic Algorithm,” IEEE Congress on Evolutionary Computation (CEC), 2020.
12. [12] S. Nagae, D. Kanda, S. Kawai, and H. Nobuhara, “Automatic layer selection for transfer learning and quantitative evaluation of layer effectiveness,” Neurocomputing, Vol.469, pp. 151-162, 2022.
13. [13] A. Krizhevsky, “Learning Multiple Layers of Features from Tiny Images,” Master’s Thesis, University of Toronto, 2009.
14. [14] M. Tan, R. Pang, and Q. V. Le, “Efficientdet: Scalable and efficient object detection,” Proc. of the IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 10781-10790, 2020.
15. [15] T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollár, and C. L. Zitnick, “Microsoft COCO: Common Objects in Context,” D. Fleet, T. Pajdla, B. Schiele, and T. Tuytelaars (Eds.), “Computer Vision – ECCV 2014,” pp. 740-755, Springer Cham, 2014.
16. [16] E. David, S. Madec, P. Sadeghi-Tehran, H. Aasen, B. Zheng, S. Liu, N. Kirchgessner, G. Ishikawa, K. Nagasawa, and M. A. Badhon, “Global Wheat Head Detection (GWHD) dataset: a large and diverse dataset of high-resolution RGB-labelled images to develop and benchmark wheat head detection methods,” Plant Phenomics, Article No.3521852, 2020.
17. [17] I. Ryuji, N. Hajime, and K. Shigeru, “Genetic Algorithm Based Automatic Layer Selection of Transfer Learning for Object Detection,” The 7th Int. Workshop on Advanced Computational Intelligence and Intelligent Informatics (IWACIII), Article No.M2-3-5, 2021.
18. [18] M. Tan and Q. Le, “Efficientnet: Rethinking model scaling for convolutional neural networks,” Proc. of the 36th Int. Conf. on Machine Learning (PMLR), Vol.97, pp. 6105-6114, 2019.
19. [19] T. DeVries and G. W. Taylor, “Improved regularization of convolutional neural networks with cutout,” arXiv:1708.04552, 2017.
20. [20] S. Yun, D. Han, S. J. Oh, S. Chun, J. Choe, and Y. Yoo, “Cutmix: Regularization strategy to train strong classifiers with localizable features,” Proc. of the IEEE/CVF Int. Conf. on Computer Vision (ICCV), pp. 6023-6032, 2019.
21. [21] I. Loshchilov and F. Hutter, “Decoupled Weight Decay Regularization,” Int. Conf. on Learning Representations (ICLR), 2019.
22. [22] “Global Wheat Detection,” https://www.kaggle.com/c/global-wheat-detection [accessed March 15, 2022]