請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/81045完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 丁建均(Jian-Jiun Ding) | |
| dc.contributor.author | Hao-Wen Chia | en |
| dc.contributor.author | 賈皓文 | zh_TW |
| dc.date.accessioned | 2022-11-24T03:27:49Z | - |
| dc.date.available | 2021-09-01 | |
| dc.date.available | 2022-11-24T03:27:49Z | - |
| dc.date.copyright | 2021-09-01 | |
| dc.date.issued | 2021 | |
| dc.date.submitted | 2021-08-26 | |
| dc.identifier.citation | [1] Yann LeCun, Yoshua Bengio, et al. Convolutional networks for images, speech, and time series. The handbook of brain theory and neural networks, 3361(10):1995, 1995. [2] Jonathan Long, Evan Shelhamer, and Trevor Darrell. Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3431–3440, 2015. [3] Wayne Wu, Chen Qian, Shuo Yang, Quan Wang, Yici Cai, and Qiang Zhou. Look at boundary: A boundary-aware face alignment algorithm. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2129– 2138, 2018. [4] Xinyao Wang, Liefeng Bo, and Li Fuxin. Adaptive wing loss for robust face alignment via heatmap regression. In Proceedings of the IEEE/CVF international conference on computer vision, pages 6971–6981, 2019. [5] Timothy F Cootes, Christopher J Taylor, David H Cooper, and Jim Graham. Active shape models-their training and application. Computer vision and image understanding, 61(1):38–59, 1995. [6] Vahid Kazemi and Josephine Sullivan. One millisecond face alignment with an ensemble of regression trees. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1867–1874, 2014. [7] Ziwei Liu, Ping Luo, Xiaogang Wang, and Xiaoou Tang. Large-scale celebfaces attributes (celeba) dataset. Retrieved August, 15(2018):11, 2018. [8] Christos Sagonas, Georgios Tzimiropoulos, Stefanos Zafeiriou, and Maja Pantic. 300 faces in-the-wild challenge: The first facial landmark localization challenge. In Proceedings of the IEEE International Conference on Computer Vision Workshops, pages 397–403, 2013. [9] Ralph Gross, Iain Matthews, Jeffrey Cohn, Takeo Kanade, and Simon Baker. Multi-pie. In 2008 8th IEEE International Conference on Automatic Face Gesture Recognition, pages 1–8, 2008. [10] Timothy F Cootes, Gareth J Edwards, and Christopher J Taylor. Active appearance models. In European conference on computer vision, pages 484–498. Springer, 1998. [11] Piotr Doll´ar, Peter Welinder, and Pietro Perona. Cascaded pose regression. In 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pages 1078–1085. IEEE, 2010. [12] Alejandro Newell, Kaiyu Yang, and Jia Deng. Stacked hourglass networks for human pose estimation. In European conference on computer vision, pages 483–499. Springer, 2016. [13] Zhiqiang Tang, Xi Peng, Shijie Geng, Lingfei Wu, Shaoting Zhang, and Dimitris Metaxas. Quantized densely connected u-nets for efficient landmark localization. In Proceedings of the European Conference on Computer Vision (ECCV), pages 339–354, 2018. [14] Roberto Valle, Jose M Buenaposada, Antonio Valdes, and Luis Baumela. A deeply-initialized coarse-to-fine ensemble of regression trees for face alignment. In Proceedings of the European Conference on Computer Vision (ECCV), pages 585–601, 2018. [15] Weijian Li, Yuhang Lu, Kang Zheng, Haofu Liao, Chihung Lin, Jiebo Luo, Chi-Tung Cheng, Jing Xiao, Le Lu, Chang-Fu Kuo, et al. Structured landmark detection via topology-adapting deep graph learning. In Computer Vision– ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part IX 16, pages 266–283. Springer, 2020. [16] Zhen-Hua Feng, Josef Kittler, Muhammad Awais, Patrik Huber, and XiaoJun Wu. Wing loss for robust facial landmark localisation with convolutional neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 2235–2245, 2018. [17] Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, Fran¸cois Laviolette, Mario Marchand, and Victor Lempitsky. Domain-adversarial training of neural networks. The journal of machine learning research, 17(1):2096–2030, 2016. [18] Xinyao Wang, Liefeng Bo, and Li Fuxin. Adaptive wing loss for robust face alignment via heatmap regression. In The IEEE International Conference on Computer Vision (ICCV), October 2019. [19] Sina Honari, Pavlo Molchanov, Stephen Tyree, Pascal Vincent, Christopher Pal, and Jan Kautz. Improving landmark localization with semi-supervised learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 1546–1555, 2018. [20] Istv´an S´ar´andi, Timm Linder, Kai O Arras, and Bastian Leibe. Synthetic occlusion augmentation with volumetric heatmaps for the 2018 eccv posetrack challenge on 3d human pose estimation. arXiv preprint arXiv:1809.04987, 2018. [21] Jie Zhang, Shiguang Shan, Meina Kan, and Xilin Chen. Coarse-to-fine autoencoder networks (cfan) for real-time face alignment. In European conference on computer vision, pages 1–16. Springer, 2014. [22] Xiangyu Zhu, Zhen Lei, Xiaoming Liu, Hailin Shi, and Stan Z Li. Face alignment across large poses: A 3d solution. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 146–155, 2016. [23] Shaoqing Ren, Xudong Cao, Yichen Wei, and Jian Sun. Face alignment at 3000 fps via regressing local binary features. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 1685–1692, 2014. [24] Shizhan Zhu, Cheng Li, Chen Change Loy, and Xiaoou Tang. Face alignment by coarse-to-fine shape searching. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4998–5006, 2015. [25] Zhanpeng Zhang, Ping Luo, Chen Change Loy, and Xiaoou Tang. Facial landmark detection by deep multi-task learning. In European conference on computer vision, pages 94–108. Springer, 2014. [26] Sina Honari, Jason Yosinski, Pascal Vincent, and Christopher Pal. Recombinator networks: Learning coarse-to-fine feature aggregation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 5743–5752, 2016. [27] Xin Miao, Xiantong Zhen, Xianglong Liu, Cheng Deng, Vassilis Athitsos, and Heng Huang. Direct shape regression networks for end-to-end face alignment. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 5040–5049, 2018. [28] Shengju Qian, Keqiang Sun, Wayne Wu, Chen Qian, and Jiaya Jia. Aggregation via separation: Boosting facial landmark detector with semi-supervised style translation. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 10153–10163, 2019. [29] Wenyan Wu and Shuo Yang. Leveraging intra and inter-dataset variations for robust face alignment. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pages 150–159, 2017. [30] Xuanyi Dong, Yan Yan, Wanli Ouyang, and Yi Yang. Style aggregated network for facial landmark detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 379–388, 2018. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/81045 | - |
| dc.description.abstract | 對於各種臉部分析問題，面部標點及輪廓位置都是十分重要，包括臉部表情偵測、頭部姿態估計、面部變形、面部反偽造以及身份檢測。近年來，基於深度學習的人臉關鍵點檢測有著不錯的成效，然而由於標記資料的有限性，預測還是存在著侷限。受近期所流行的自學習方法的影響，我們提出一種半監督式學習的人臉關鍵點預測方法。 在我們的方法中，我們會先利用標記資料訓練一個教導模組，並將未標記數據帶入教導模組中產生偽標籤。產生偽標籤後，我們設計了兩個篩選偽標籤的方法，包括利用Pearson卡方檢測計算預測區域與標準高斯分布的差距，以及利用數據增強前後預測結果的差異做篩選。獲得偽標籤後，我們將標記資料跟偽標籤資料一起訓練學生模組，學生模組得到的結果較教導模組進步5.5%. 除了半監督式學習的方法，我們還提出了一個遮擋區域損失增加的方法，如此我們可以更好處理遮蔽的問題。 | zh_TW |
| dc.description.provenance | Made available in DSpace on 2022-11-24T03:27:49Z (GMT). No. of bitstreams: 1 U0001-2308202117253900.pdf: 14247893 bytes, checksum: bc0bbdbc9ec12f79d0703f21182fbd0f (MD5) Previous issue date: 2021 | en |
| dc.description.tableofcontents | CONTENTS Chapter 1 Introduction 1 1.1 Facial Landmark Datasets 2 1.2 Evaluation Metrics 2 1.2.1 Normalized Mean Error 2 1.2.2 Failure Rate 4 Chapter 2 Related Methods 5 2.1 Direct Regression 5 2.2 Heatmap Regression 6 2.3 CNN-based Heatmap Regression Models 7 2.4 Boundary Information 8 2.5 Loss Functions for Landmark Detection 8 2.6 Semi-Supervision 10 2.7 Domain Adaptation 10 2.7.1 Domain-Adversarial Training of Neural Network (DANN) 11 Chapter 3 Proposed Methods 13 3.1 Landmark Detection System 13 3.2 Semi-Supervised Approach 16 3.2.1 Confidence Sifting Mechanism 16 3.2.2 Augmentation Sifting Mechanism 18 3.3 Occlusion Loss Enhancement 23 Chapter 4 Simulation Results 26 4.1 Datasets 26 4.1.1 300W dataset 26 4.1.2 WFLW dataset 28 4.1.3 CelebA dataset 29 4.2 Implementation Details 30 4.3 Evaluation Results 30 4.3.1 Semi-Supervised Results on the 300W dataset 30 4.3.2 Semi-Supervised Results on the WFLW dataset 31 4.3.3 Occlusion Loss Enhancement Results 34 4.4 Experimental Problem Results 36 4.4.1 Transfer Learning Method 37 4.4.2 Domain Adaptation Method 39 Chapter 5 Conclusion 41 Reference 42 | |
| dc.language.iso | en | |
| dc.subject | 遮擋區域損失增加 | zh_TW |
| dc.subject | 人臉關鍵點檢測 | zh_TW |
| dc.subject | 半監督式學習方法 | zh_TW |
| dc.subject | 偽標籤篩選方法 | zh_TW |
| dc.subject | sifting mechanisms | en |
| dc.subject | Facial landmark detection | en |
| dc.subject | occlusion loss enhancement | en |
| dc.subject | semi-supervised algorithm | en |
| dc.title | 利用半監督式學習進行人臉關鍵點偵測 | zh_TW |
| dc.title | Semi-Supervised Learning for Facial Landmark with Confidence and Augmentation Sifting Mechanisms | en |
| dc.date.schoolyear | 109-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 張榮吉(Hsin-Tsai Liu),余執彰(Chih-Yang Tseng),歐陽良昱 | |
| dc.subject.keyword | 人臉關鍵點檢測,半監督式學習方法,偽標籤篩選方法,遮擋區域損失增加, | zh_TW |
| dc.subject.keyword | Facial landmark detection,semi-supervised algorithm,sifting mechanisms,occlusion loss enhancement, | en |
| dc.relation.page | 46 | |
| dc.identifier.doi | 10.6342/NTU202102638 | |
| dc.rights.note | 同意授權(限校園內公開) | |
| dc.date.accepted | 2021-08-26 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 電信工程學研究所 | zh_TW |
| 顯示於系所單位： | 電信工程學研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-2308202117253900.pdf 授權僅限NTU校內IP使用（校園外請利用VPN校外連線服務） | 13.91 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。