Một số hướng phát triển cho đồ án bao gồm:
− Mở rộng bộ dữ liệu với nhiều lớp đối tượng trong văn bản.
− Tìm hiểu các phương pháp để tăng cường bộ dữ liệu (data augumentation) − Phân tích, thống kê các lỗi, tìm cách giải quyết để cải thiện mô hình.
− Tiếp tục tìm hiểu và cài đặt thêm các thuật toán OD khác để tìm ra phương pháp đạt kết quả tốt nhất.
52
TÀI LIỆU THAM KHẢO
[1]Redmon J, Divvala S, Girshick R, et al. “You only look once: Unified, real-time object detection” [C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 779-788.
[2]Redmon J, Farhadi A. “YOLO9000: better, faster, stronger” [C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 7263- 7271.
[3] Redmon J, Farhadi A. Yolov3: An incremental improvement[J]. arXiv preprint arXiv:1804.02767, 2018.
[4]Alexey Bochkovskiy, Chien-Yao Wang, Hong-Yuan Mark Liao. “YOLOv4: Optimal Speed and Accuracy of Object Detection” 23 Apr 2020 :arXiv:2004.10934.
[5] Ross Girshick, Jeff Donahue, Trevor Darrell, Jitendra Malik. “Rich feature hierarchies for accurate object detection and semantic segmentation”[C]// The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014, pp. 580-587.
[6]Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," NATURE, vol. 521, no.7553, pp. 436-444, 2015.
[7]Vaibhaw Singh Chandel, “Selective Search for Object Detection (C++ / Python)” 18 09 2017. [Online]. Available: https://www.learnopencv.com/selective-search- for-object-detection-cpp-python/
[8]Arden Dertat, "Applied Deep Learning - Part 1: Artificial Neural Networks," 08 08 2017. [Online]. Available: https://towardsdatascience.com.
[9]Oleksii Sheremet, “Intersection over union (IoU) calculation for evaluating an image segmentation model ”Jul 25 2020. [Online]. Available:https://towardsdatascience.com/intersection-over-union-iou-
calculation-for-evaluating-an-image-segmentation-model-822e2e84686
[10] Tsung-Yi Lin, Piotr Dollar , Ross Girshick , Kaiming He, Bharath Hariharan , and Serge Belongie, “Feature Pyramid Networks for Object Detection”
53
[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 1063-6919.
[11] Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun, “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks” [C]//Proceedings of the IEEE conference on computer vision and pattern recognition. arXiv:1506.01497v3, 2016.
[12] Stanford CS class CS231n: Convolutional Neural Networks for Visual Recognition, “Neural Networks Part 1: Setting up the Architecture ”. [Online]. Available: https://cs231n.github.io/neural-networks-1/
[13] Michael Copeland, “What’s the Difference Between Artificial Intelligence, Machine Learning and Deep Learning?” , July 29, 2016. [Online]. Available:https://blogs.nvidia.com/blog/2016/07/29/whats-difference-artificial- intelligence-machine-learning-deep-learning-ai/
[14] Arthur Ouaknine, “Review of Deep Learning Algorithms for Object Detection”, Feb 5, 2018. [Online]. Available: https://medium0.com/zylapp/review-of-deep-learning-algorithms-for-object-
detection-c1f3d437b852
[15] Prabhu, “Understanding of Convolutional Neural Network (CNN) — Deep Learning” , Mar 4, 2018. [Online]. Available: https://medium0.com/@RaghavPrabhu/understanding-of-convolutional-neural-
network-cnn-deep-learning-99760835f148
[16] Adrian Rosebrock , “Intersection over Union (IoU) for object detection”, 2016 [Online]. Available: https://www.pyimagesearch.com/2016/11/07/intersection- over-union-iou-for-object-detection/
[17] Paolo F. Valdez, “Apple defect detection using deep learning-based object detection for better post har-vest handling”, ICLR Conference, arXiv:2005.06089, May 2020.
54
[18] Patrick Poirson, Phil Ammirato,… “Fast Single Shot Detection and Pose Estimation” 2016 Fourth International Conference on 3D Vision, (3DV) – IEEE, arXiv:1609.05590v, Sep 2016.
[19] Gao Huang, Zhuang Liu, Laurens van der Maaten, Kilian Q. Weinberger , “Densely Connected Convolutional Networks”, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, arXiv:1608.06993, Jan 2018.
[20] Alexey Bochkovskiy, Chien-Yao Wang, Hong-Yuan Mark Liao, “Scaled- YOLOv4: Scaling Cross Stage Partial Network”, 22 Feb 2021, arXiv:2011.08036v2,