臺灣博碩士論文加值系統

摘要 i
ABSTRACT ii
誌謝 iv
目錄 v
表目錄 vii
圖目錄 viii
1 第一章 緒論 1
1.1 研究背景與動機 1
1.2 研究目的 2
1.3 論文架構 3
2 第二章 文獻探討 4
2.1 調節梯度衝突策略 4
2.1.1 PCGrad 4
2.1.2 Recon 7
2.2 梯度修正方向最佳化策略 9
2.2.1 MGDA 9
2.2.2 CAGrad 10
2.3 梯度量級平衡策略 11
2.3.1 DWA 11
2.3.2 GradNorm 12
2.3.3 AdaTask 12
3 第三章 研究方法 14
3.1 複合式多任務學習策略 14
3.1.1 取得共享參數層任務梯度 14
3.1.2 調節衝突梯度 15
3.1.3 梯度方向最佳化 16
3.1.4 平衡梯度量級 18
3.1.5 複合式多任務學習策略流程 19
3.2 通道梯度衝突調節機制 24
3.2.1 模型通道衝突概念 24
3.2.2 通道梯度衝突紀錄 27
3.2.3 通道梯度衝突選定 30
3.2.4 通道梯度向量衝突調節策略 33
4 第四章 實驗與分析 34
4.1 資料集 34
4.1.1 CityScapes公開資料集 34
4.1.2 NYUv2公開資料集 34
4.2 模型準確度指標 35
4.2.1 單任務準確度指標 35
4.2.2 多任務策略指標 38
4.3 實驗數據與分析 39
4.3.1 SegNet骨幹網路雙任務模型實驗 40
4.3.2 MTAN骨幹網路三任務模型實驗 41
4.3.3 PSPNet骨幹網路三任務實驗 44
4.3.4 YOLOv7骨幹網路三任務模型實驗 46
5 第五章 結論與未來工作 48
5.1 結論 48
5.2 未來工作 49
參考文獻 50

[1]R. Caruana, "Multitask learning," Machine learning, vol. 28, pp. 41-75, 1997.
[2]Y. Zhang and Q. Yang, "An overview of multi-task learning," National Science Review, vol. 5, no. 1, pp. 30-43, 2018.
[3]T. P. Lillicrap, A. Santoro, L. Marris, C. J. Akerman, and G. Hinton, "Backpropagation and the brain," Nature Reviews Neuroscience, vol. 21, no. 6, pp. 335-346, 2020.
[4]T. Yu, S. Kumar, A. Gupta, S. Levine, K. Hausman, and C. Finn, "Gradient surgery for multi-task learning," Advances in Neural Information Processing Systems, vol. 33, pp. 5824-5836, 2020.
[5] S. Guangyuan, Q. Li, W. Zhang, J. Chen, and X.-M. Wu, "Recon: Reducing Conflicting Gradients From the Root For Multi-Task Learning," in The Eleventh International Conference on Learning Representations, 2022.
[6]Z. Chen et al., "Just pick a sign: Optimizing deep multitask models with gradient sign dropout," Advances in Neural Information Processing Systems, vol. 33, pp. 2039-2050, 2020.
[7]B. Liu, X. Liu, X. Jin, P. Stone, and Q. Liu, "Conflict-averse gradient descent for multi-task learning," Advances in Neural Information Processing Systems, vol. 34, pp. 18878-18890, 2021.
[8]O. Sener and V. Koltun, "Multi-task learning as multi-objective optimization," Advances in neural information processing systems, vol. 31, 2018.
[9] M. Cordts et al., "The cityscapes dataset for semantic urban scene understanding," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 3213-3223.
[10]M. Ehrgott, Multicriteria optimization. Springer Science & Business Media, 2005.
[11]H. M. Hochman and J. D. Rodgers, "Pareto optimal redistribution," The American economic review, vol. 59, no. 4, pp. 542-557, 1969.
[12] M. Jaggi, "Revisiting Frank-Wolfe: Projection-free sparse convex optimization," in International conference on machine learning, 2013: PMLR, pp. 427-435.
[13] S. Liu, E. Johns, and A. J. Davison, "End-to-end multi-task learning with attention," in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 1871-1880.
[14] Z. Chen, V. Badrinarayanan, C.-Y. Lee, and A. Rabinovich, "Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks," in International conference on machine learning, 2018: PMLR, pp. 794-803.
[15] E. Yang et al., "Adatask: A task-aware adaptive learning rate approach to multi-task learning," in Proceedings of the AAAI Conference on Artificial Intelligence, 2023, vol. 37, no. 9, pp. 10745-10753.
[16]V. Badrinarayanan, A. Kendall, and R. Cipolla, "Segnet: A deep convolutional encoder-decoder architecture for image segmentation," IEEE transactions on pattern analysis and machine intelligence, vol. 39, no. 12, pp. 2481-2495, 2017.
[17] N. Silberman, D. Hoiem, P. Kohli, and R. Fergus, "Indoor segmentation and support inference from rgbd images," in Computer Vision–ECCV 2012: 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part V 12, 2012: Springer, pp. 746-760.
[18] D. Senushkin, N. Patakin, A. Kuznetsov, and A. Konushin, "Independent Component Alignment for Multi-Task Learning," in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 20083-20093.
[19] H. Zhao, J. Shi, X. Qi, X. Wang, and J. Jia, "Pyramid scene parsing network," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 2881-2890.
[20] A. Kendall, Y. Gal, and R. Cipolla, "Multi-task learning using uncertainty to weigh losses for scene geometry and semantics," in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 7482-7491.
[21]B. Lin, Y. Feiyang, and Y. Zhang, "A closer look at loss weighting in multi-task learning," 2021.
[22] L. Liu et al., "Towards impartial multi-task learning," 2021: iclr.
[23]A. Navon et al., "Multi-task learning as a bargaining game," arXiv preprint arXiv:2202.01017, 2022.
[24] C.-Y. Wang, A. Bochkovskiy, and H.-Y. M. Liao, "YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors," in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 7464-7475.