輕量化卷積神經網路的少樣本人臉辨識

以作者查詢圖書館館藏

、以作者查詢臺灣博碩士

、以作者查詢全國書目

、勘誤回報

、線上人數：47

、訪客IP：3.14.145.97

姓名

林宸嘉(Chen-Jia Lin) 查詢紙本館藏

畢業系所

資訊工程學系在職專班

論文名稱

輕量化卷積神經網路的少樣本人臉辨識
(Few-shot Face Recognition based on A Lightweight Convolutional Neural Network)

相關論文

★ 適用於大面積及場景轉換的視訊錯誤隱藏法	★ 虛擬觸覺系統中的力回饋修正與展現
★ 多頻譜衛星影像融合與紅外線影像合成	★ 腹腔鏡膽囊切除手術模擬系統
★ 飛行模擬系統中的動態載入式多重解析度地形模塑	★ 以凌波為基礎的多重解析度地形模塑與貼圖
★ 多重解析度光流分析與深度計算	★ 體積守恆的變形模塑應用於腹腔鏡手術模擬
★ 互動式多重解析度模型編輯技術	★ 以小波轉換為基礎的多重解析度邊線追蹤技術(Wavelet-based multiresolution edge tracking for edge detection)
★ 基於二次式誤差及屬性準則的多重解析度模塑	★ 以整數小波轉換及灰色理論為基礎的漸進式影像壓縮
★ 建立在動態載入多重解析度地形模塑的戰術模擬	★ 以多階分割的空間關係做人臉偵測與特徵擷取
★ 以小波轉換為基礎的影像浮水印與壓縮	★ 外觀守恆及視點相關的多重解析度模塑

檔案

[Endnote RIS 格式]

[Bibtex 格式]

[相關文章]

[文章引用]

[完整記錄]

[館藏目錄]

[檢視]

[下載]

本電子論文使用權限為同意立即開放。
已達開放權限電子全文僅授權使用者為學術研究之目的，進行個人非營利性質之檢索、閱讀、列印。
請遵守中華民國著作權法之相關規定，切勿任意重製、散佈、改作、轉貼、播送，以免觸法。

摘要(中)

隨著科技進步，生活自動化的需求越來越普及，人臉辨識 (face recognition) 儼然也成為各種自動化應用中不可或缺的一部份，並且已被廣泛地應用在多種不同場域中。近年來，在深度學習的蓬勃發展帶動下，為了追求更高的辨識準確度，人臉辨識也大量引入深度學習的技術。在大量深度學習模式的評比下，為了更進一步提升準確度，網路模型的複雜度也一再被提升，網路階層變得更深、特徵數量變得更多，硬體規格的需求也一再增加。另一方面，由於隱私權的問題，人臉照片取得不易。鑒於前述問題，促使我們提出輕量化卷積神經網路的少樣本人臉辨識系統，主要研究內容就是如何在輕量化模型與少樣本的學習情形下還能提高人臉辨識的準確率 (accuracy)。
本論文主要內容分為兩部份：第一部份為人臉辨識的網路架構，以MobileFaceNet 為骨幹並做進一步的輕量化，移除最後的升維 11 卷積層，藉此減少網路的模型大小，並加上通道注意力的 ECA-Net 模組 (module)，能夠在輕量化卷積神經網路的同時，還能保有準確率；並以此 ECA-MobileFaceNet-S 模型作為特徵擷取器，將人臉照片輸入此模型得到特徵向量。之後根據餘弦相似度 (cosine similarity) 做比對分類。第二部份為少樣本學習，為了改善少樣本學習的問題，使用增大角度邊界間距的 ProtoNets 訓練方法取代原先平方歐式距離的 Prototypical Networks 訓練方法，以達到特徵擷取器能讓 “群內聚集、群間分離” 的效果，以提升人臉辨識能力。
我們的輕量化網路模型參數量比 MobileFaceNet 網路減少了 13.39%；在增大角度邊界間距的 ProtoNets 訓練方法與 large angular margin loss 的效果下，相比於原先平方歐式距離的 Prototypical Networks 訓練方法，在 LFW 資料集上的準確度提高了 10.79%。

摘要(英)

With the progression of technology, the demand for life automation has become more and more popular, and face recognition has become an indispensable part of various automation applications and has been widely used in many different fields. In recent years, the development of deep learning is booming, in order to pursue the accuracy, face recognition has also introduced a large number of deep learning techniques. The network models were modified deeper and deeper, the number of parameters were continuously increased, and the requirements for hardware specifications were then upgraded again and again. On the other hand, it is hard to obtain face photos due to the privacy issues.
To solve the problems, we propose a few-shot face recognition system based on a lightweight convolutional neural network, and mainly study how to improve the accuracy of face recognition in the case of lightweight models and few-shot learning. At first, we take MobileFaceNet as the backbone and remove the final 11 convolutional layer, thereby reducing the model size, and added ECA-Net modules to maintaining the accuracy. We call this new model ECA-MobileFaceNet-S. We can input face photos into the model to obtain the feature vectors, and then classify according to their cosine similarity. Then, to improve the few-shot learning problems, we refer to Prototypical Networks and replace the square Euclidean distance with large angular margin loss to improve the face recognition ability.
We reduce the parameters of the original MobileFaceNet by 13.39%. Compared to the Prototypical Networks, the accuracy on the LFW dataset is improved by 10.79% under the effect of ProtoNets training method and the large angular margin loss.

關鍵字(中)

★ 少樣本

關鍵字(英)

論文目次

摘要 i
Abstract ii
致謝 iii
目錄 iv
圖目錄 vi
表目錄 viii
第一章緒論 1
1.1 研究動機 1
1.2 系統架構 2
1.3 論文架構 3
第二章相關研究 4
2.1 卷積神經網路的輕量化 4
2.2 深度學習的注意力機制 7
2.3 元學習 11
第三章人臉辨識的網路架構 14
3.1 MobileNet v2 架構 14
3.2 MobileFaceNet 架構 17
3.3 ECA-MobileFaceNet-S 架構 20
第四章少樣本學習 24
4.1 度量學習 24
4.2 基於度量的元學習 29
4.3 增大角度邊界間距的 ProtoNets 31
第五章實驗與結果 35
5.1 實驗設備介紹 35
5.2 輕量化卷積神經網路之訓練 36
5.3 少樣本學習的比較和評估 37
第六章結論及未來展望 46
參考文獻 47

參考文獻

[1] S. Chen, Y. Liu, X. Gao, and Z. Han, “MobileFaceNets: efficient CNNs for accurate real-time face verification on mobile devices,” arXiv: 1804.07573, 2018.
[2] Q. Wang, B. Wu, P. Zhu, P. Li, W. Zuo, and Q. Hu, “ECA-Net: efficient channel attention for deep convolutional neural networks,” arXiv: 1910.03151v4, 2019.
[3] J. Snell, K. Swersky, and R. S. Zemel, “Prototypical networks for few-shot learning,” arXiv: 1502.01852, 2015.
[4] A. Krizhevsky, I. Sutskever, and G. E. Hinton, ”ImageNet classification with deep convolutional neural networks,“ in Proc. Neural Information Processing Systems (NIPS), Lake Tahoe, Nevada, Dec.3-8, 2012, pp.1097-1105.
[5] F. N. Iandola, S. Han, W. Moskewicz, K. Ashraf, W. Dally, and K. Keutzer, “Squeezenet: Alexnet-level accuracy with 50x fewer parameters and 1mb model size,” arXiv: 1602.07360, 2016.
[6] O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, Al. C. Berg, and L. Fei-Fei, “ImageNet large scale visual recognition challenge,” arXiv: 1409.0575v2, 2014.
[7] A. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, and H. Adam, “Mobilenets: efficient convolutional neural networks for mobile vision applications,” arXiv: 1704.04861, 2017.
[8] X. Zhang, X. Zhou, M. Lin, and J. Sun, “ShuffleNet: an extremely efficient convolutional neural network for mobile devices,” arXiv: 1707.01083, 2017.
[9] J. Hu, L. Shen, S. Albanie, G. Sun, and E. Wu, “Squeeze-and-excitation networks,” arXiv: 1709.01507v4, 2017.
[10] S. Woo, J. Park, J. Lee, and I.S. Kweon, “CBAM: convolutional block attention module,” arXiv: 1807.06521v2, 2018.
[11] R. Vilalta and Y. Drissi, “A perspective view and survey of meta-learning,” Artificial Intelligence Review, vol.18, pp.77-95, 2002.
[12] J. Vanschoren, “Meta-learning: a survey,” arXiv: 1810.03548v1, 2018.
[13] T. Hospedales, A. Antoniou, P. Micaelli, and A. Storkey, “Meta-learning in neural networks: a survey,” arXiv: 2004.05439v 2, 2020.
[14] M. Huisman, J. N. van Rijn, and A. Plaat, “A survey of deep meta-learning,” arXiv: 2010.03522v2, 2020.
[15] S. Hochreiter, A. S. Younger, and P. R. Conwell, “Learning to learn using gradient descent,” in Proc. Int. Conf. on Artificial Neural Networks, Vienna, Austria, Aug.21-25, 2001, pp.87-94.
[16] M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.C. Chen, “MobileNetV2: inverted residuals and linear bottlenecks,” arXiv: 1801.04381, 2018.
[17] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” arXiv: 1512.03385, 2015.
[18] M. Lin, Q. Chen, and S. Yan, “Network in network,” arXiv: 1312.4400, 2013.
[19] K. He, X. Zhang, S. Ren, and J. Sun, “Delving deep into rectifiers: surpassing human-level performance on ImageNet classification,” arXiv: 1502.01852, 2015.
[20] V. Nair and G. E. Hinton, “Rectified linear units improve restricted Boltzmann machines,” in Proc. Int. Conf. on Machine Learning (ICML), Haifa, Israel, June 21-24, 2010, pp.807-814.
[21] J. Deng, J. Guo, N. Xue, and S. Zafeiriou, “ArcFace: additive angular margin loss for deep face recognition,” arXiv: 1801.07698, 2018.
[22] H. 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,” arXiv: 1801.09414v2, 2018.
[23] W. Liu, Y. Wen, Z. Yu, and M. Yang, “Large-margin softmax loss for convolutional neural networks,” arXiv: 1612.02295v4, 2016.
[24] F. Schroff, D. Kalenichenko, and J. Philbin, “FaceNet: a unified embedding for face recognition and clustering,” arXiv: 1503.03832, 2015.
[25] F. Wang, W. Liu, H. Liu, and J. Cheng, “Additive margin softmax for face verification,” arXiv: 1801.05599v4, 2018.
[26] G. Koch, R. Zemel, and R. Salakhutdinov, Siamese neural networks for one-shot image recognition, Master thesis, Sci. Graduate Dept. of Computer Science, Univ. of Toronto, Canada, 2015.
[27] O. Vinyals, C. Blundell, T. Lillicrap, K. Kavukcuoglu, and D. Wierstra, “Matching networks for one shot learning,” arXiv: 1606.04080v2, 2016.
[28] F. Sung, Y. Yang, L. Zhang, T. Xiang, P. H. S. Torr, and T. M. Hospedales, “Learning to compare: relation network for few-shot learning,” arXiv: 1711.06025v2, 2017.
[29] Y. Guo, L. Zhang, Y. Hu, X. He, and J. Gao, “MS-CELEB-1M: a dataset and benchmark for large-scale face recognition,” arXiv: 1607.08221, 2016.
[30] 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, Univ. of Massachusetts, Amherst, May, 2007.

指導教授

曾定章(Din-Chang Tseng)

審核日期

2021-7-28

推文