請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/81037完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 李綱(Kang li) | |
| dc.contributor.author | Tsung-Yu Lin | en |
| dc.contributor.author | 林宗郁 | zh_TW |
| dc.date.accessioned | 2022-11-24T03:27:24Z | - |
| dc.date.available | 2021-09-02 | |
| dc.date.available | 2022-11-24T03:27:24Z | - |
| dc.date.copyright | 2021-09-02 | |
| dc.date.issued | 2021 | |
| dc.date.submitted | 2021-08-24 | |
| dc.identifier.citation | [1] 花蓮分局秘書室, 經濟部標檢局, 無人駕駛時代來臨！《無人載具科技創新實驗條例》三讀通過, January 2019, https://www.bsmi.gov.tw/bsmiGIP/wSite/ct?xItem=77314 ctNode=7941 mp=1. [2] EBC東森電視, 東森新聞, 國道車禍！特斯拉煞不住 車身「穿破」貨車頂, June 2020, https://news.ebc.net.tw/news/society/212290 [3] Hendrycks, D., Gimpel, K. “A baseline for detecting misclassified and out-ofdistribution examples in neural networks.” International Conference on Learning Representations, ICLR. 2017. [4] Corbi`ere, C., Thome, N., Bar-Hen, A., Cord, M., P´erez, P. “Addressing failure prediction by learning model confidence.” Advances in Neural Information Processing Systems. 2019. [5] Geifman, Y., El-Yaniv, R. “Selective classification for deep neural networks.” Advances in Neural Information Processing Systems. 2017. [6] Jiang, H., Kim, B., Guan, M., Gupta, M. “To trust or not to trust a classifier.” Advances in Neural Information Processing Systems. 2018. [7] John S. Denker and Yann LeCun “Transforming Neural-Net Output Levels to Probability Distributions.” Advances in Neural Information Processing Systems. 1991. [8] David JC MacKay “A Practical Bayesian Framework for Backpropagation Networks.” Neural Computation, 4(3):448– 472. 1992. [9] David JC Mackay “Bayesian Neural Networks and Density Networks.” Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 354(1):73–80. 1995. [10] Graves, A. “Practical variational inference for neural networks.” Advances in Neural Information Processing Systems. pp. 2348–2356. 2011. [11] Blundell, C., Cornebise, J., Kavukcuoglu, K., Wierstra, D. “Weight uncertainty in neural networks.” arXiv preprint arXiv:1505.05424. 2015. [12] Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. “Dropout: A Simple Way to Prevent Neural Networks from Overfitting.” Journal of Machine Learning Research, 15:1929–1958. 2014. [13] Gal, Y., Ghahramani, Z. “Dropout as a bayesian approximation: Representing model uncertainty in deep learning.” 33rd International Conference on Machine Learning, ICML 2016. vol. 3, pp. 1651–1660. 2016. [14] Gal, Y., Ghahramani, Z. “Bayesian convolutional neural networks with bernoulli approximate variational inference.” arXiv preprint arXiv:1506.02158. 2015. [15] Kendall, A., Badrinarayanan, V., Cipolla, R. “Bayesian segnet: Model uncertainty in deep convolutional encoder-decoder architectures for scene understanding.” arXiv preprint arXiv:1511.02680. 2015. [16] Alex Kendall, Vijay Badrinarayanan, and Roberto Cipolla. Bayesian Segnet “Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding.” arXiv Preprint, 1511.02680. 2015. [17] Alex Kendall and Yarin Gal. “What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?” Advances in Neural Information Processing Systems. 2017. [18] Shuya Isobe and Shuichi Arai. “A Semantic Segmentation Method Using Model Uncertainty.” IIAE International Conference on Intelligent Systems and Image Processing. 2017. [19] Shuya Isobe and Shuichi Arai. “Deep Convolutional EncoderDecoder Network with Model Uncertainty for Semantic Segmentation.” IEEE International Conference on INnovations in Intelligent SysTems and Applications. 2017. [20] Shuya Isobe and Shuichi Arai. “Inference with Model Uncertainty on Indoor Scene for Semantic Segmentation.” IEEE Global Conference on Signal and Information Processing. 2017. [21] Jungo, A., Meier, R., Ermis, E., Herrmann, E., Reyes, M. “Uncertainty-driven sanity check: Application to postoperative brain tumor cavity segmentation.” arXiv preprint arXiv:1806.03106. 2018. [22] Kwon, Y., Won, J.H., Kim, B.J., Paik, M.C. “Uncertainty quantification using bayesian neural networks in classification: Application to biomedical image segmentation.” Computational Statistics and Data Analysis. 2020. [23] Kohlberger, T., Singh, V., Alvino, C., Bahlmann, C., Grady, L. “Evaluating segmentation error without ground truth.” International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI. 2012 [24] Robinson, R., Oktay, O., Bai, W., Valindria, V.V., Sanghvi, M.M., Aung, N., Paiva, J.M., Zemrak, F., Fung, K., Lukaschuk, E., et al. “Real-time prediction of segmentation quality.” International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI. 2018 [25] Huang, Z., Huang, L., Gong, Y., Huang, C., Wang, X. “Mask scoring r-cnn.” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR. 2019. [26] Jiang, B., Luo, R., Mao, J., Xiao, T., Jiang, Y. “Acquisition of localization confidence for accurate object detection.” Proceedings of the European Conference on Computer Vision, ECCV. 2018. [27] Chabrier, S., Emile, B., Rosenberger, C., Laurent, H. “Unsupervised performance evaluation of image segmentation.” EURASIP Journal on Applied Signal Processing. 2006 [28] Gao, H., Tang, Y., Jing, L., Li, H., Ding, H. “A novel unsupervised segmentation quality evaluation method for remote sensing images.” Sensors. 2017. [29] Liu, F., Xia, Y., Yang, D., Yuille, A.L., Xu, D. “An alarm system for segmentation algorithm based on shape model.” Proceedings of the IEEE International Conference on Computer Vision, ICCV. 2019. [30] Kingma, D.P., Welling, M. “Auto-encoding variational bayes.” International Conference on Learning Representations, ICLR. 2014. [31] DeVries, T., Taylor, G.W. “Learning confidence for out-of-distribution detection in neural networks.” arXiv preprint arXiv:1802.04865. 2018. [32] Hendrycks, D., Mazeika, M., Dietterich, T. “Deep anomaly detection with outlier exposure.” International Conference on Learning Representations, ICLR. 2019 [33] Baur, C., Wiestler, B., Albarqouni, S., Navab, N. “Deep autoencoding models for unsupervised anomaly segmentation in brain mr images.” MICCAI Brainlesion Workshop. 2018. [34] Haselmann, M., Gruber, D.P., Tabatabai, P. “Anomaly detection using deep learning based image completion.” International Conference on Machine Learning and Applications, ICMLA. IEEE. 2018. [35] Lis, K., Nakka, K., Fua, P., Salzmann, M. “Detecting the unexpected via image resynthesis.” Proceedings of the IEEE International Conference on Computer Vision. pp. 2152–2161. 2019. [36] Yingda Xia, Yi Zhang, Fengze Liu, Wei Shen, and Alan Yuille. “Synthesize then compare: Detecting failures and anomalies for semantic segmentation.” arXiv preprint arXiv:2003.08440. 2020. [37] David Haldimann, Hermann Blum, Roland Siegwart, and Cesar Cadena. “This is not what i imagined: Error detection for semantic segmentation through visual dissimilarity.” arXiv:1909.00676v1. 2019. [38] Otsu, Nobuyuki. 'A threshold selection method from gray-level histograms.' IEEE transactions on systems, man, and cybernetics 9.1: 62-66. 1979 [39] Dhanachandra, Nameirakpam, Khumanthem Manglem, and Yambem Jina Chanu. 'Image segmentation using K-means clustering algorithm and subtractive clustering algorithm.' Procedia Computer Science 54: 764-771. 2015. [40] E. Romera, J. M. Alvarez, L. M. Bergasa, and R. Arroyo. “Erfnet: Efficient residual factorized convnet for real-time semantic segmentation,” IEEE Transactions on Intelligent Transportation Systems, vol. 19, no. 1, pp. 263–272. 2017. [41] S. Mehta, M. Rastegari, A. Caspi, L. Shapiro, and H. Hajishirzi. “Espnet: Efficient spatial pyramid of dilated convolutions for semantic segmentation,” Proceedings of the European Conference on Computer Vision, pp. 552–568. 2018. [42] C. Yu, C. Gao, J. Wang, G. Yu, C. Shen, and N. Sang. “Bisenet v2: Bilateral network with guided aggregation for real-time semantic segmentation.” arXiv preprint arXiv:2004.02147. 2020. [43] R. P. Poudel, S. Liwicki, and R. Cipolla, “Fast-scnn: Fast semantic segmentation network.” arXiv preprint arXiv:1902.04502. 2019. [44] A. G. 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 preprint arXiv:1704.04861. 2017. [45] X. Zhang, X. Zhou, M. Lin, and J. Sun. “Shufflenet: An extremely efficient convolutional neural network for mobile devices.” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6848–6856. 2018. [46] F. Chollet. “Xception: Deep learning with depthwise separable convolutions.” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 1251–1258. 2017. [47] Hong, Y., Pan, H., Sun, W., Jia, Y. “Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes.” arXiv preprint arXiv:2101.06085. 2021. [48] Goodfellow, Ian J., et al. 'Generative adversarial networks.' arXiv preprint arXiv:1406.2661. 2014. [49] Mirza, Mehdi, and Simon Osindero. 'Conditional generative adversarial nets.' arXiv preprint arXiv:1411.1784. 2014. [50] Liu, X., Yin, G., Shao, J., Wang, X., et al. “Learning to predict layout-to-image conditional convolutions for semantic image synthesis.” Advances in Neural Information Processing Systems. 2019. [51] Park, T., Liu, M.Y., Wang, T.C., Zhu, J.Y. “Semantic image synthesis with spatially-adaptive normalization.” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR. 2019. [52] Wang, T.C., Liu, M.Y., Zhu, J.Y., Tao, A., Kautz, J., Catanzaro, B. “Highresolution image synthesis and semantic manipulation with conditional gans.” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR. 2018. [53] Geifman, Yonatan, and Ran El-Yaniv. 'Selective classification for deep neural networks.' arXiv preprint arXiv:1705.08500. 2017. [54] Long, Jonathan, Evan Shelhamer, and Trevor Darrell. 'Fully convolutional networks for semantic segmentation.' Proceedings of the IEEE conference on computer vision and pattern recognition. 2015. [55] Chao, Ping, et al. 'Hardnet: A low memory traffic network.' Proceedings of the IEEE/CVF International Conference on Computer Vision. 2019. [56] Huang, Gao, et al. 'Densely connected convolutional networks.' Proceedings of the IEEE conference on computer vision and pattern recognition. 2017. [57] T.-C. Wang, M.-Y. Liu, J.-Y. Zhu, A. Tao, J. Kautz, and B. Catanzaro. “High-resolution image synthesis and semantic manipulation with conditional gans.” In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2018. [58] Lin, Tsung-Yi, et al. 'Feature pyramid networks for object detection.' Proceedings of the IEEE conference on computer vision and pattern recognition. 2017. [59] He, Kaiming, et al. 'Deep residual learning for image recognition.' Proceedings of the IEEE conference on computer vision and pattern recognition. 2016. [60] El-Yaniv, R., Wiener, Y., Lugosi, G. (Ed.). “On the foundations of noise-free selective classification.” Journal of Machine Learning Research, 11, Article 1605-1641. 2010. [61] O. Gascuel and G. Caraux. “Distribution-free performance bounds with the resubstitution error estimate.” Pattern Recognition Letters, 13:757–764. 1992. [62] Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., Schiele, B. “The cityscapes dataset for semantic urban scene understanding.” In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR. 2016. [63] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. “Gradient-based learning applied to document recognition.” Proc. IEEE, vol. 86, no. 11, pp. 2278–2324. 1998. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/81037 | - |
| dc.description.abstract | 現今的語意分割方法因缺乏偵測錯誤以及輸出信心指數的能力，較難以實際運用到許多安全至上的應用中，例如:自動駕駛。因此本研究針對這些問題，提出了一套語意分割錯誤偵測框架，讓使用者可以透過對輸出設定一個特定的閾值，了解到此語意分割模型對於現在的環境辨識狀況，信心指數，以及哪些東西是辨識錯誤的。本研究的框架透過生成式對抗網路還原語意分割的結果，並藉由一個比較模組比較原始圖像與重新生成的圖像以預測每個像素的信心指數，最後利用選擇性分類選定一個合適的閾值以判定圖中哪些像素為辨識錯誤。其中本研究提出了一個嶄新的比較模組SiameseFPN，能夠針對原始圖像與生成圖像進行更好的分辨，達到更好的效能，最終在Cityscape資料集中達到AUC=93.61、AUPR-ERROR=58.92以及FPR95=22.39，均為現今方法中的最佳，並且能在單張NVIDIA RTX 2080Ti 顯示卡上達到30FPS以上的推論速度，可以應用在大部分的實時語意分割模型。 | zh_TW |
| dc.description.provenance | Made available in DSpace on 2022-11-24T03:27:24Z (GMT). No. of bitstreams: 1 U0001-2408202120393500.pdf: 3597412 bytes, checksum: f0b9f86a2da96c7c9e61b23067d326f6 (MD5) Previous issue date: 2021 | en |
| dc.description.tableofcontents | 口試委員會審定書 # 誌謝 i 摘要 ii ABSTRACT iii 目錄 iv 圖目錄 vi 表目錄 viii Chapter 1 緒論 1 1.1 研究背景 1 1.2 研究動機與目的 2 1.3 研究貢獻 3 Chapter 2 文獻回顧 4 2.1 失效偵測(Failures detection)與異常物體檢測(Out-Of-Distribution (OOD) detection) 4 2.1.1 不確定性估測(Uncertainty estimation) 6 2.1.2 影像分割品質評估(Semantic segmentation quality assessment) 7 2.1.3 異常偵測(Out-Of-Distribution (OOD) / Anomaly detection) 7 2.2 實時語意分割(Real-time semantic segmentation) 8 2.2.1 編碼解碼結構(Encoder-decoder architecture) 9 2.2.2 雙分支結構(Two-pathway architecture) 10 2.2.3 輕量化編碼器 10 2.3 條件生成式對抗網路(Conditional Generative Adversarial Network) 11 Chapter 3 神經網路系統架構與研究方法 13 3.1 語意分割錯誤偵測框架 13 3.1.1 語意分割模組(Semantic Segmentation Module) 14 3.1.2 圖像生成模組(Image Synthesis Module) 20 3.1.3 比較模組(Comparison Module) - SiameseFPN 22 3.2 選擇性分類 24 3.2.1 Risk-Coverage curve 24 3.2.2 Selection with Guaranteed Risk (SGR)演算法 25 3.3 訓練方法 28 3.3.1 訓練語意分割模組 28 3.3.2 訓練圖像生成模組 29 3.3.3 訓練比較模組 30 3.4 評估指標 32 3.4.1 AUC (Area Under ROC Curve) 33 3.4.2 AUPR (Area Under PR Curve) 35 3.4.3 FPR95 (false positive rate at 95% true positive rate) 37 Chapter 4 實驗結果與分析 38 4.1 實驗設置 38 4.1.1 資料集介紹 38 4.1.2 模型架構 39 4.1.3 比較對象 39 4.1.4 評估指標 39 4.1.5 硬體配置 40 4.2 模型性能表現 40 4.2.1 模型效能表現分析 40 4.2.2 模型基於選擇分類之效能表現分析 41 4.2.3 錯誤偵測分析 42 4.3 模型運算量與運算速度比較 44 4.4 模型輸出結果可視化 49 Chapter 5 結論與未來建議 52 5.1 結論 52 5.2 未來建議 52 參考資料 53 | |
| dc.language.iso | zh-TW | |
| dc.subject | 語意分割 | zh_TW |
| dc.subject | 生成式對抗網路 | zh_TW |
| dc.subject | 選擇性分類 | zh_TW |
| dc.subject | 異常偵測 | zh_TW |
| dc.subject | 錯誤辨識 | zh_TW |
| dc.subject | generative adversarial network | en |
| dc.subject | failure detection | en |
| dc.subject | anomaly detection | en |
| dc.subject | selective classification | en |
| dc.subject | semantic segmentation | en |
| dc.title | 以生成式對抗網路與選擇性分類技術之實時語意分割錯誤偵測 | zh_TW |
| dc.title | Real-time Semantic Segmentation Fault Detection Using Generative Adversarial Network and Selective Classification Techniques | en |
| dc.date.schoolyear | 109-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 蘇偉儁(Hsin-Tsai Liu),李坤彥(Chih-Yang Tseng) | |
| dc.subject.keyword | 語意分割,錯誤辨識,異常偵測,選擇性分類,生成式對抗網路, | zh_TW |
| dc.subject.keyword | semantic segmentation,failure detection,anomaly detection,selective classification,generative adversarial network, | en |
| dc.relation.page | 58 | |
| dc.identifier.doi | 10.6342/NTU202102692 | |
| dc.rights.note | 同意授權(限校園內公開) | |
| dc.date.accepted | 2021-08-25 | |
| dc.contributor.author-college | 工學院 | zh_TW |
| dc.contributor.author-dept | 機械工程學研究所 | zh_TW |
| 顯示於系所單位： | 機械工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-2408202120393500.pdf 授權僅限NTU校內IP使用（校園外請利用VPN校外連線服務） | 3.51 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。