請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/49687完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 徐宏民(Winston Hsu) | |
| dc.contributor.author | Yu-Sheng Lin | en |
| dc.contributor.author | 林與晟 | zh_TW |
| dc.date.accessioned | 2021-06-15T11:42:02Z | - |
| dc.date.available | 2020-08-21 | |
| dc.date.copyright | 2020-08-21 | |
| dc.date.issued | 2020 | |
| dc.date.submitted | 2020-08-13 | |
| dc.identifier.citation | [1] P. L. Bartlett, F. C. N. Pereira, C. J. C. Burges, L. Bottou, and K. Q. Weinberger, editors. Advances in Neural Information Processing Systems 25: 26th Annual Con- ference on Neural Information Processing Systems 2012. Proceedings of a meeting held December 3-6, 2012, Lake Tahoe, Nevada, United States, 2012. [2] W. Brendel and M. Bethge. Approximating cnns with bag-of-local-features models works surprisingly well on imagenet. International Conference on Learning Repre- sentations, 2019. [3] Q. Cao, L. Shen, W. Xie, O. M. Parkhi, and A. Zisserman. Vggface2: A dataset for recognising faces across pose and age. In 2018 13th IEEE International Conference on Automatic Face Gesture Recognition (FG 2018), pages 67–74. IEEE, 2018. [4] G. Castañón and J. Byrne. Visualizing and quantifying discriminative features for face recognition. 2018 13th IEEE International Conference on Automatic Face | Gesture Recognition (FG 2018), pages 16–23, 2018. [5] Y.-L. Chang, Z. Y. Liu, K.-Y. Lee, and W. Hsu. Free-form video inpainting with 3d gated convolution and temporal patchgan. In Proceedings of the International Conference on Computer Vision (ICCV), 2019. [6] A.Chattopadhay,A.Sarkar,P.Howlader,andV.N.Balasubramanian.Grad-cam++: Generalized gradient-based visual explanations for deep convolutional networks. In 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pages 839–847, March 2018. [7] B. Chen, C. Chen, and W. H. Hsu. Face recognition and retrieval using cross-age reference coding with cross-age celebrity dataset. IEEE Transactions on Multimedia, 17(6):804–815, 2015. [8] J. Deng, J. Guo, X. Niannan, and S. Zafeiriou. Arcface: Additive angular margin loss for deep face recognition. In CVPR, 2019. [9] J. Deng, Y. Zhou, and S. P. Zafeiriou. Marginal loss for deep face recognition. 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pages 2006–2014, 2017. [10] D. Gu, Y. Li, F. Jiang, Z. Wen, S. Liu, W. Shi, G. Lu, and C. Zhou. Vinet: A visually interpretable image diagnosis network. IEEE Transactions on Multimedia, 22(7):1720–1729, 2020. [11] D. Gunning. Explainable artificial intelligence (xai). Defense Advanced Research Projects Agency (DARPA), nd Web, 2, 2017. [12] Y. Guo, L. Zhang, Y. Hu, X. He, and J. Gao. Ms-celeb-1m: A dataset and benchmark for large-scale face recognition. In ECCV, 2016. [13] K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, June 27-30, 2016, pages 770–778, 2016. [14] M. Hind, D. Wei, M. Campbell, N. C. F. Codella, A. Dhurandhar, A. Mojsilović, K. Natesan Ramamurthy, and K. R. Varshney. Ted: Teaching ai to explain its deci- sions. In Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society, AIES ’19, pages 123–129, New York, NY, USA, 2019. ACM. [15] G. Hinton, O. Vinyals, and J. Dean. Distilling the knowledge in a neural network. In NIPS Deep Learning and Representation Learning Workshop, 2015. [16] G. B. Huang, M. Ramesh, T. Berg, and E. Learned-Miller. Labeled faces in the wild: A database for studying face recognition in unconstrained environments. Technical Report 07-49, University of Massachusetts, Amherst, October 2007. [17] R. Huang, S. Zhang, T. Li, and R. He. Beyond face rotation: Global and local perception gan for photorealistic and identity preserving frontal view synthesis. In The IEEE International Conference on Computer Vision (ICCV), Oct 2017. [18] M. Kan, S. Shan, H. Chang, and X. Chen. Stacked progressive auto-encoders (spae) for face recognition across poses. 2014 IEEE Conference on Computer Vision and Pattern Recognition, pages 1883–1890, 2014. [19] N. Kumar, A. C. Berg, P. N. Belhumeur, and S. K. Nayar. Attribute and simile classifiers for face verification. In 2009 IEEE 12th International Conference on Computer Vision, pages 365–372, 2009. [20] W. Liu, Y. Wen, Z. Yu, M. Li, B. Raj, and L. Song. Sphereface: Deep hypersphere embedding for face recognition. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. [21] X. Liu, X. Wang, and S. Matwin. Improving the interpretability of deep neural net- works with knowledge distillation. 2018 IEEE International Conference on Data Mining Workshops (ICDMW), pages 905–912, 2018. [22] C. Lu and X. Tang. Surpassing human-level face verification performance on lfw with gaussian face. In Proceedings of the Twenty-Ninth AAAI Conference on Artifi- cial Intelligence, AAAI’15, pages 3811–3819. AAAI Press, 2015. [23] A.M.MartinezandR.Benavente.Thearfacedatabase.Tech.Rep.24CVCTechnical Report, 01 1998. [24] S. Moschoglou, A. Papaioannou, C. Sagonas, J. Deng, I. Kotsia, and S. Zafeiriou. Agedb: The first manually collected, in-the-wild age database. In 2017 IEEE Con- ference on Computer Vision and Pattern Recognition Workshops (CVPRW), pages 1997–2005, July 2017. [25] O.M.Parkhi,A.Vedaldi,andA.Zisserman.Deepfacerecognition.InBMVC,2015. [26] S. Ren, K. He, R. B. Girshick, and J. Sun. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell., 39(6):1137–1149, 2017. [27] M. T. Ribeiro, S. Singh, and C. Guestrin. ”why should i trust you?”: Explaining the predictions of any classifier. In Proceedings of the 22Nd ACM SIGKDD Inter- national Conference on Knowledge Discovery and Data Mining, KDD ’16, pages 1135–1144, New York, NY, USA, 2016. ACM. [28] R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra. Grad- cam: Visual explanations from deep networks via gradient-based localization. In 2017 IEEE International Conference on Computer Vision (ICCV), pages 618–626, Oct 2017. [29] S. Sengupta, J. Chen, C. Castillo, V. M. Patel, R. Chellappa, and D. W. Jacobs. Frontal to profile face verification in the wild. In 2016 IEEE Winter Conference on Applications of Computer Vision (WACV), pages 1–9, March 2016. [30] E. Shelhamer, J. Long, and T. Darrell. Fully convolutional networks for semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell., 39(4):640–651, 2017. [31] Y. Sun, Y. Chen, X. Wang, and X. Tang. Deep learning face representation by joint identification-verification. In Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, December 8-13 2014, Montreal, Quebec, Canada, pages 1988–1996, 2014. [32] H. J. Wang, Y. Wang, Z. Zhou, X. Ji, D. Gong, J. Zhou, Z. Li, and W. Liu. Cosface: Large margin cosine loss for deep face recognition. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5265–5274, 2018. [33] Y. Wen, K. Zhang, Z. Li, and Y. Qiao. A discriminative feature learning approach for deep face recognition. In ECCV, 2016. [34] L. Wolf, T. Hassner, and I. Maoz. Face recognition in unconstrained videos with matched background similarity. CVPR 2011, pages 529–534, 2011. [35] D.Yi,Z.Lei,S.Liao,andS.Z.Li.Learningfacerepresentationfromscratch.ArXiv, abs/1411.7923, 2014. [36] B. Yin*, L. Tran*, H. Li, X. Shen, and X. Liu. Towards interpretable face recog- nition. In In Proceeding of International Conference on Computer Vision, Seoul, South Korea, October 2019. [37] K. Zhang, Z. Zhang, Z. Li, and Y. Qiao. Joint face detection and alignment us- ing multitask cascaded convolutional networks. IEEE Signal Processing Letters, 23(10):1499–1503, Oct 2016. [38] T. Zheng, W. Deng, and J. Hu. Cross-age LFW: A database for studying cross-age face recognition in unconstrained environments. CoRR, abs/1708.08197, 2017. [39] B. Zhou, A. Khosla, A. Lapedriza, A. Oliva, and A. Torralba. Learning Deep Fea- tures for Discriminative Localization. arXiv e-prints, page arXiv:1512.04150, Dec 2015. [40] Z.Zhu,P.Luo,X.Wang,andX.Tang.Deeplearningidentity-preservingfacespace. In 2013 IEEE International Conference on Computer Vision, pages 113–120, 2013. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/49687 | - |
| dc.description.abstract | 我們在人臉識別任務上，特別是人臉驗證任務，研究了XAI（可解釋AI）。臉部驗證是近年來一項至關重要的任務，並且已被部署到許多應用程序中，例如訪問控制，監視和針對移動設備的自動個人登錄。隨著數據量的增加，深度卷積神經網絡可以針對人臉驗證任務實現非常高的準確性。但除了出色的性能外，深層驗證模型還需要更多的可解釋性，以讓我們信任它產生的結果。在本文中，我們提出一種新穎的相似性度量，稱為可解釋餘弦（xCos），它帶有一個可學習的模組，並可將其插入大多數驗證模型中，以提供有意義的解釋。在xCos的幫助下，我們可見兩張輸入臉部圖片的哪些部分是相似的、模型注意的部位，以及模型如何加權局部相似度以輸出xCos分數。我們證明了我們提出的方法在LFW和各種人臉驗證資料集上的有效性：所提出的模型不僅為人臉驗證提供了新穎而理想的模型可解釋性，並且確保了插入現有人臉識別模型時的準確性。 | zh_TW |
| dc.description.abstract | We study the XAI (explainable AI) on the face recognition task, particularly the face verification here. Face verification is a crucial task in recent days and it has been deployed to plenty of applications, such as access control, surveillance, and automatic personal log-on for mobile devices. With the increasing amount of data, deep convolutional neural networks can achieve very high accuracy for the face verification task. Beyond exceptional performances, deep face verification models need more interpretability so that we can trust the results they generate. In this paper, we propose a novel similarity metric, called explainable cosine (xCos), that comes with a learnable module that can be plugged into most of the verification models to provide meaningful explanations. With the help of xCos, we can see which parts of the 2 input faces are similar, where the model pays its attention to, and how the local similarities are weighted to form the output xCos score. We demonstrate the effectiveness of our proposed method on LFW and various competitive benchmarks, resulting in not only providing novel and desiring model interpretability for face verification but also ensuring the accuracy as plugging into existing face recognition models. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-15T11:42:02Z (GMT). No. of bitstreams: 1 U0001-1208202008514500.pdf: 2129282 bytes, checksum: 7a69629bcbbe8ef0c6328025959b1016 (MD5) Previous issue date: 2020 | en |
| dc.description.tableofcontents | 誌謝 iii 摘要 iv Abstract v 1 Introduction 1 2 Related Work 4 2.1 Face Verification 4 2.2 Explainable AI 4 3 Proposed approach 7 3.1 Ideal xCos Metric 7 3.2 xCos Candidates 7 3.3 Network Architecture 9 4 Experiment 12 4.1 Implementation Details 12 4.2 Datasets 12 4.3 Date Preprocessing 12 4.4 CNN Setup 13 4.5 xCos Module Setup 13 4.6 Quantitative Results 14 4.7 Face Verification Performance 14 4.8 Ablation Studies 15 4.9 Computational Cost 15 4.10 Qualitative Results 16 4.11 Visualizations of xCos 16 4.12 Comparison with Saliency Methods 17 5 Discussions 19 5.1 Additional Robustness to Occlusion 19 5.2 How to Adapt xCos From Frontal Images to Profile Ones 20 6 Conclusion 21 Bibliography 22 | |
| dc.language.iso | zh-TW | |
| dc.subject | 人臉驗證 | zh_TW |
| dc.subject | 電腦視覺 | zh_TW |
| dc.subject | 人臉辨識 | zh_TW |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | 可解釋人工智慧 | zh_TW |
| dc.subject | Face Verification | en |
| dc.subject | Computer Vision | en |
| dc.subject | Explainable AI | en |
| dc.subject | Deep Learning | en |
| dc.subject | Face Recognition | en |
| dc.title | xCos：適用於人臉驗證任務的可解釋餘弦相似度 | zh_TW |
| dc.title | xCos: An Explainable Cosine Metric for Face Verification Task | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 108-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.author-orcid | 0000-0001-6379-4774 | |
| dc.contributor.oralexamcommittee | 余能豪(NENG-HAO YU),葉梅珍(Mei-Chen Yeh),陳文進(Wen-Chin Chen) | |
| dc.subject.keyword | 可解釋人工智慧,人臉驗證,電腦視覺,深度學習,人臉辨識, | zh_TW |
| dc.subject.keyword | Explainable AI,Face Verification,Computer Vision,Face Recognition,Deep Learning, | en |
| dc.relation.page | 26 | |
| dc.identifier.doi | 10.6342/NTU202003045 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2020-08-13 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 資訊網路與多媒體研究所 | zh_TW |
| 顯示於系所單位： | 資訊網路與多媒體研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-1208202008514500.pdf 未授權公開取用 | 2.08 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。