請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/70807完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 徐宏民 | |
| dc.contributor.author | Kaipeng Zhang | en |
| dc.contributor.author | 張凱鵬 | zh_TW |
| dc.date.accessioned | 2021-06-17T04:39:14Z | - |
| dc.date.available | 2018-08-24 | |
| dc.date.copyright | 2018-08-24 | |
| dc.date.issued | 2018 | |
| dc.date.submitted | 2018-08-07 | |
| dc.identifier.citation | [1] A. Bansal, A. Nanduri, C. Castillo, R. Ranjan, and R. Chellappa. Umdfaces: An annotated face dataset for training deep networks. arXiv:1611.01484, 2016.
[2] J. Bruna, P. Sprechmann, and Y. LeCun. Super-resolution with deep convolutional sufficient statistics. ICLR, 2016. [3] L. Chang and D. Y. Tsao. The code for facial identity in the primate brain. Cell, 169(6):1013–1028, 2017. [4] B.-C. Chen, C.-S. Chen, and W. H. Hsu. Face recognition and retrieval using crossage reference coding with cross-age celebrity dataset. TMM, 17(6):804–815, 2015. [5] L. Chunjie, Y. Qiang, et al. Cosine normalization: Using cosine similarity instead of dot product in neural networks. arXiv, 2017. [6] C. Dong, C. C. Loy, and X. Tang. Accelerating the super-resolution convolutional neural network. In ECCV, pages 391–407, 2016. [7] I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio. Generative adversarial nets. In NIPS, pages 2672– 2680, 2014. [8] K. He, X. Zhang, S. Ren, and J. Sun. Delving deep into rectifiers: Surpassing humanlevel performance on imagenet classification. In ICCV, pages 1026–1034, 2015. [9] K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. In CVPR, pages 770–778, 2016. [10] G. Huang, Z. Liu, r. K. Weinberge, and L. v. d. Maaten. Densely connected convolutional networks. 2017. [11] G. B. Huang and E. Learned-Miller. Labeled faces in the wild: Updates and new reporting procedures. Dept. Comput. Sci., Univ. Massachusetts Amherst, Amherst, MA, USA, Tech. Rep, pages 14–003, 2014. [12] J. Johnson, A. Alahi, and L. Fei-Fei. Perceptual losses for real-time style transfer and super-resolution. In ECCV, pages 694–711, 2016. [13] A. Krizhevsky, I. Sutskever, and G. E. Hinton. Imagenet classification with deep convolutional neural networks. In NIPS, pages 1097–1105, 2012. [14] N. Kumar, A. C. Berg, P. N. Belhumeur, and S. K. Nayar. Attribute and simile classifiers for face verification. ICCV, 2009. [15] W.-S. Lai, J.-B. Huang, N. Ahuja, and M.-H. Yang. Deep laplacian pyramid networks for fast and accurate super-resolution. CVPR, 2017. [16] C. Ledig, L. Theis, F. Huszár, J. Caballero, A. Cunningham, A. Acosta, A. Aitken, A. Tejani, J. Totz, Z. Wang, et al. Photo-realistic single image super-resolution using a generative adversarial network. 2017. [17] Y. Li, C. Cai, G. Qiu, and K.-M. Lam. Face hallucination based on sparse local-pixel structure. PR, 47(3):1261–1270, 2014. [18] C. Liu, H.-Y. Shum, and W. T. Freeman. Face hallucination: Theory and practice. IJCV, 75(1):115–134, 2007. [19] W. Liu, Y. Wen, Z. Yu, M. Li, B. Raj, and L. Song. Sphereface: Deep hypersphere embedding for face recognition. 2017. [20] W. Liu, Y.-M. Zhang, X. Li, Z. Yu, B. Dai, T. Zhao, and L. Song. Deep hyperspherical learning. In NIPS, pages 3953–3963, 2017. [21] Z. Liu, P. Luo, X. Wang, and X. Tang. Deep learning face attributes in the wild. In ICCV, pages 3730–3738, 2015. [22] X. Ma, J. Zhang, and C. Qi. Hallucinating face by position-patch. PR, 43(6):2224– 2236, 2010. [23] O. M. Parkhi, A. Vedaldi, and A. Zisserman. Deep face recognition. In BMVC, volume 1, page 6, 2015. [24] S. Ren, K. He, R. Girshick, and J. Sun. Faster r-cnn: Towards real-time object detection with region proposal networks. In NIPS, pages 91–99, 2015. [25] O. Rippel, M. Paluri, P. Dollar, and L. Bourdev. Metric learning with adaptive density discrimination. ICLR, 2016. [26] M. S. Sajjadi, B. Scholkopf, and M. Hirsch. Enhancenet: Single image superresolution through automated texture synthesis. In ICCV, pages 4491–4500, 2017. [27] F. Schroff, D. Kalenichenko, and J. Philbin. Facenet: A unified embedding for face recognition and clustering. In CVPR, pages 815–823, 2015. [28] Y. Sun, X. Wang, and X. Tang. Deeply learned face representations are sparse, selective, and robust. In CVPR, pages 2892–2900, 2015. [29] Y. Taigman, M. Yang, M. Ranzato, and L. Wolf. Deepface: Closing the gap to human-level performance in face verification. In CVPR, pages 1701–1708, 2014. [30] M. F. Tappen and C. Liu. A bayesian approach to alignment-based image hallucination. In ECCV, pages 236–249, 2012. [31] L. Van Der Maaten. Accelerating t-sne using tree-based algorithms. JMLR, 15(1):3221–3245, 2014. [32] Y. Wen, K. Zhang, Z. Li, and Y. Qiao. A discriminative feature learning approach or deep face recognition. In ECCV, pages 499–515, 2016. [33] L. Wolf, T. Hassner, and I. Maoz. Face recognition in unconstrained videos with matched background similarity. In CVPR, pages 529–534, 2011. [34] C.-Y. Yang, S. Liu, and M.-H. Yang. Structured face hallucination. In ECVP, pages 1099–1106, 2013. [35] D. Yi, Z. Lei, S. Liao, and S. Z. Li. Learning face representation from scratch. arXiv:1411.7923, 2014. [36] X. Yu and F. Porikli. Ultra-resolving face images by discriminative generative networks. In ECCV, pages 318–333, 2016. [37] K. Zhang, Z. Zhang, Z. Li, and Y. Qiao. Joint face detection and alignment using multitask cascaded convolutional networks. SPL, 23(10):1499–1503, 2016. [38] E. Zhou, H. Fan, Z. Cao, Y. Jiang, and Q. Yin. Learning face hallucination in the wild. In AAAI, pages 3871–3877, 2015. [39] S. Zhu, S. Liu, C. C. Loy, and X. Tang. Deep cascaded bi-network for face hallucination. In ECCV, pages 614–630, 2016. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/70807 | - |
| dc.description.abstract | 人臉超解析是一個生成任務，它目標是對低解析度的人臉超解析。而人在觀察一個人臉的時候會下意識地著重在人臉的身份資訊上。然而現有的人臉超解析方法都忽略了身份資訊的恢復。本論文提出身份超解析網路來對身份資訊進行恢復。特別地，我們定義了一個身份超解析損失函數來衡量超解析人臉和高解析度人臉的身份資訊的差異。這種差異的度量是在超球度量空間上進行。然而，直接使用這個損失函數會導致一個動態的域分叉問題。這是由於超解析度域和真實高解度域之間存在很大的差距。為了克服這個問題，我們提出了域整合訓練方法。它可以為這兩個不同的域建立一個魯棒的身份度量空間。通過充分的實驗驗證，我們的方法在放大12x14像素的人臉八倍的時候比其它方法取得更好的視覺效果。此外，我們的方法顯著地提升了低分辨度人臉的可辨識能度。 | zh_TW |
| dc.description.abstract | Face hallucination is a generative task to super-resolve the facial image with low resolution while human perception of face heavily relies on identity information. However, previous face hallucination approaches largely ignore facial identity recovery. This paper proposes Super-Identity Convolutional Neural Network (SICNN) to recover identity information for generating faces closed to the real identity. Specifically, we define a super-identity loss to measure the identity difference between a hallucinated face and its corresponding high-resolution face within the hypersphere identity metric space. However, directly using this loss will lead to a Dynamic Domain Divergence problem, which is caused by the large margin between the high-resolution domain and the hallucination domain. To overcome this challenge, we present a domain-integrated training approach by constructing a robust identity metric for faces from these two domains. Extensive experimental evaluations demonstrate that the proposed SICNN achieves superior hallucination visual quality over the state-of-the-art methods on a challenging task to super-resolve 12x14 faces with an 8x upscaling factor. In addition, SICNN significantly improves the recognizability of ultra-low-resolution faces. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-17T04:39:14Z (GMT). No. of bitstreams: 1 ntu-107-R05944047-1.pdf: 3069519 bytes, checksum: 26f3caf51d4c5598a99d6ca3884ce175 (MD5) Previous issue date: 2018 | en |
| dc.description.tableofcontents | 口試委員會審定書iii
誌謝v Acknowledgements vii 摘要ix Abstract xi 1 Introduction 1 2 Related Works 5 3 Super-Identity CNN 7 3.1 Face Hallucination Network Architecture . . . . . . . . . . . . . . . . . 7 3.2 Super-Resolution Loss . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 3.3 Hypersphere Identity Metric Space . . . . . . . . . . . . . . . . . . . . . 9 3.4 Super-Identity Loss . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 3.5 Challenges of Training with Super-Identity Loss . . . . . . . . . . . . . . 11 3.6 Domain-Integrated Training Algorithm . . . . . . . . . . . . . . . . . . . 13 3.7 Comparison to Adversarial Training . . . . . . . . . . . . . . . . . . . . 14 4 Experiments 17 4.1 Training Details . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17 4.2 Testing Details . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18 4.3 Ablation Experiment . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18 4.4 Evaluation on Face Hallucination . . . . . . . . . . . . . . . . . . . . . . 19 4.5 Evaluation on Identity Recovery . . . . . . . . . . . . . . . . . . . . . . 21 4.6 Evaluation on Identity Recognizability . . . . . . . . . . . . . . . . . . . 21 4.7 Evaluation on Low-Resolution Face Recognition . . . . . . . . . . . . . 22 Bibliography 25 | |
| dc.language.iso | zh-TW | |
| dc.subject | 卷積類神經網路 | zh_TW |
| dc.subject | 身份超解析 | zh_TW |
| dc.subject | 人臉超解析 | zh_TW |
| dc.subject | Super-Identity | en |
| dc.subject | Face Hallucination | en |
| dc.subject | Convolutional Neural Network | en |
| dc.title | 基於身份超解析之卷積類神經網路的人臉超解析 | zh_TW |
| dc.title | Super-Identity Convolutional Neural Network for Face Hallucination | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 106-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 陳文進,葉梅珍 | |
| dc.subject.keyword | 身份超解析,人臉超解析,卷積類神經網路, | zh_TW |
| dc.subject.keyword | Super-Identity,Face Hallucination,Convolutional Neural Network, | en |
| dc.relation.page | 28 | |
| dc.identifier.doi | 10.6342/NTU201802101 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2018-08-07 | |
| 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 | |
|---|---|---|---|
| ntu-107-1.pdf 未授權公開取用 | 3 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。