跳到主要內容

臺灣博碩士論文加值系統

(44.200.194.255) 您好!臺灣時間:2024/07/19 04:53
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:趙大衛
研究生(外文):Da-Wei Jaw
論文名稱:應用於低能見度之夜晚暨降雪情況的無監督式對抗學習和創新訓練機制之交互作用技術
論文名稱(外文):Deep Unsupervised Learning Techniques for Image-to-image and Object Detection in Snowy and Dark Conditions
指導教授:郭斯彥郭斯彥引用關係黃士嘉黃士嘉引用關係
指導教授(外文):Sy-Yen KuoShih-Chia Huang
口試委員:鍾偉和林昌鴻游家牧顏嗣鈞雷欽隆王家慶洪澤權
口試委員(外文):Wei-Ho ChungChang-Hong LinChia-Mu YuHsu-Chun YenChin-Laung LeiJia-Ching WangPatrick Hung
口試日期:2023-07-10
學位類別:博士
校院名稱:國立臺灣大學
系所名稱:電機工程學系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2023
畢業學年度:111
論文頁數:68
中文關鍵詞:無監督式學習生成對抗網路低能見度物件偵測影像能見度增強
外文關鍵詞:Unsupervised learningGenerative adversarial networksLow-visibility object detectionImage visibility enhancement
DOI:10.6342/NTU202301347
相關次數:
  • 被引用被引用:0
  • 點閱點閱:81
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
物件偵測技術已經被廣泛使用在真實世界的各種電腦視覺系統中。然而,應用在真實世界的物件偵測技術不可避免的會遭遇到各種不同低能見度情況,例如起霧、降雨、降雪或是夜晚情況,這些都可能導致偵測系統的準確度降低,甚至給出錯誤的偵測結果。本篇博士論文從兩個不同角度來應對低能見度下的物件偵測任務挑戰,分別是對影像的能見度增強方法的研發與對應用在物件偵測網路的訓練策略研發。對於影像能見度增強方法的探討,本論文將聚焦於解決影像特性最多變的問題:單影像除雪問題。具體而言,本論文透過金字塔階層的網路架構設計和生成對抗網路驅動的訓練機制來結合無監督式的對抗式訓練,藉此極大的增強了網路對於真實世界降雪影像的特徵泛化能力與改善了輸出影像的品質。在低能見度情況的物件偵測網路之訓練策略的研發方面,本論文將會針對夜晚的低能見度情況進行方法的設計與分析,並提出了一個應用於多資料域的物件偵測框架,以及一個應用於多域資料的無監督式特徵域知識蒸餾框架。前者透過無監督式的生成對抗訓練來將低能見度的特徵域轉化到充足亮度的特徵域中,並透過訓練策略的設計來確保特徵域的語意資訊在訓練過程間的一致性;後者則是結合了生成對抗式訓練與知識蒸餾方法的特性,設計一個定向的無監督式特徵域知識蒸餾框架,並提出了一個基於物件區域的多尺度識別器來強化知識蒸餾框架,使整個知識蒸餾過程能對物件本身進行,而不被和物件偵測任務較不相關的背景資訊所干擾。本篇博士論文成功結合了生成對抗網路架構的無監督式域轉換能力,並提出了創新的網路架構,為低能見度下的物件偵測技術提供了全面的解決方案。實驗證明,本論文提出的方法無論在影像能見度強化任務或是低能見度下的物件偵測任務上,都能達到比以往方法更高的泛化能力、更有效的特徵抓取能力以及獲得更準確的結果。此外,由於提出的訓練策略具有即插即用的特性,能夠適應各種物件偵測網路架構,且不會增加額外的計算成本,具有很高的擴展性,期待這項研究能夠成為未來相關研究的基石。
This dissertation confronts the problem of object detection in low-visibility conditions, delving into two aspects: visibility enhancement in images and the development of novel training strategies for object detectors. The first perspective presents a framework for single-image snow removal, utilizing a pyramidal hierarchical architecture and a Generative Adversarial Network (GAN)-enabled refinement stage, thereby pushing the boundaries of the current state-of-the-art in image desnowing tasks. The second perspective includes two methodologies: the initial method proposes a multi-domain object detection framework that employs GANs to convert low-luminance feature representations into their high-luminance counterparts, while integrating a novel training protocol for maintaining semantic consistency. The subsequent method develops an unsupervised feature-domain knowledge distillation approach, combining GANs and neural networks to improve generalization across different luminance conditions. This approach also proposes a region-specific multiscale discriminator for capturing object-level discrepancies. By fusing the potential of GANs with architectural innovations, this dissertation provides a comprehensive solution for object detection in low-visibility conditions, exceeding conventional approaches in terms of generalization, feature interpretability, and detection accuracy.
Verification Letter from the Oral Examination Committee i
Acknowledgements iii
摘要v
Abstract vii
Contents ix
List of Figures xiii
List of Tables xvii
Denotation xix
Chapter 1 Introduction 1
1.1 Image-to-image solution . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
1.2 Training policy solution . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6
1.3 Dissertation Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
Chapter 2 Related works 11
2.1 Atmospheric Particle Removal . . . . . . . . . . . . . . . . . . . . . . . . . . . 11
2.2 Generative Adversarial Networks . . . . . . . . . . . . . . . . . . . . . . . . . 12
2.3 Object Detection Methods . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13
2.3.1 Two-Stage Object Detection Methods . . . . . . . . . . . . . . . . . . . . . . 13
2.3.2 One-Stage Object Detection Methods . . . . . . . . . . . . . . . . . . . . . . 14
2.4 Knowledge Distillation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
2.5 Discussion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
2.5.1 Image-to-image solution . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
2.5.2 Training policy solution . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16
Chapter 3 Proposed Methods 19
3.1 Image-to-image Solution . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19
3.1.1 Descriptor . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20
3.1.2 Snow Removal Module . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23
3.1.3 Refinement Module and GANs . . . . . . . . . . . . . . . . . . . . . . . . . . 24
3.1.4 Loss functions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24
3.2 Training policy Solution . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25
3.2.1 Unsupervised Feature Transformation . . . . . . . . . . . . . . . . . . . . . . 25
3.2.1.1 Generative Adversarial Networks module . . . . . . . . . . . . . 26
3.2.1.2 Object Detection module . . . . . . . . . . . . . . . . . . . . . . 28
3.2.1.3 Training Policy . . . . . . . . . . . . . . . . . . . . . . . . . . . 30
3.2.2 Unsupervised Knowledge Distillation . . . . . . . . . . . . . . . . . . . . . . 32
3.2.2.1 Training strategy . . . . . . . . . . . . . . . . . . . . . . . . . . . 35
3.2.2.2 Region-based multiscale discriminator . . . . . . . . . . . . . . . 36
Chapter 4 Experimental Results 37
4.1 Image-to-image Solution . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37
4.1.1 Implementation Details . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37
4.1.2 Dataset . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 38
4.1.3 Ablation Study . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 38
4.1.4 Discussion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 40
4.2 Training policy Solution . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 44
4.2.1 Unsupervised Feature Transformation . . . . . . . . . . . . . . . . . . . . . . 44
4.2.1.1 Implementation details . . . . . . . . . . . . . . . . . . . . . . . 44
4.2.1.2 Proposed Dataset . . . . . . . . . . . . . . . . . . . . . . . . . . 44
4.2.1.3 Comparison with state-of-the-art methods . . . . . . . . . . . . . 45
4.2.1.4 Comparison with image enhancement methods . . . . . . . . . . . 46
4.2.1.5 Ablation study . . . . . . . . . . . . . . . . . . . . . . . . . . . . 48
4.2.2 Unsupervised Knowledge Distillation . . . . . . . . . . . . . . . . . . . . . . 50
4.2.2.1 Implementation details . . . . . . . . . . . . . . . . . . . . . . . 50
4.2.2.2 Dataset . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 51
4.2.2.3 Comparison . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 51
Chapter 5 Conclusions 55
References 57
[1] Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, and Piotr Dollár. Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision, pages 2980–2988, 2017.
[2] Redmon, Joseph and Farhadi, Ali. Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767, 2018.
[3] Shih-Chia Huang, Quoc-Viet Hoang, and Da-Wei Jaw. Self-adaptive feature trans-formation networks for object detection in low luminance images. ACM Trans. Intell. Syst. Technol., 13(1), jan 2022.
[4] Xianhui Zheng, Yinghao Liao, Wei Guo, Xueyang Fu, and Xinghao Ding. Single-image-based rain and snow removal using multi-guided filter. In Minho Lee, Akira Hirose, Zeng-Guang Hou, and Rhee Man Kil, editors, Neural Information Process-ing, pages 258–265, Berlin, Heidelberg, 2013. Springer Berlin Heidelberg.
[5] Bolun Cai, Xiangmin Xu, Kui Jia, Chunmei Qing, and Dacheng Tao. Dehazenet: An end-to-end system for single image haze removal. IEEE Transactions on Image Processing, 25(11):5187–5198, 2016.
[6] Wenhan Yang, Robby T. Tan, Jiashi Feng, Jiaying Liu, Zongming Guo, and Shuicheng Yan. Deep joint rain detection and removal from a single image. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 1685–1694, 2017.
[7] Xing Liu, Masanori Suganuma, Zhun Sun, and Takayuki Okatani. Dual residual networks leveraging the potential of paired operations for image restoration. In 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 7000–7009, 2019.
[8] Yun-Fu Liu, Da-Wei Jaw, Shih-Chia Huang, and Jenq-Neng Hwang. Desnownet: Context-aware deep network for snow removal. IEEE Transactions on Image Pro-cessing, 27(6):3064–3073, 2018.
[9] Chien-Yao Wang, Alexey Bochkovskiy, and Hong-Yuan Mark Liao. Yolov7: Train-able bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv preprint arXiv:2207.02696, 2022.
[10] You Li, Pierre Duthon, Michèle Colomb, and Javier Ibanez-Guzman. What happens for a tof lidar in fog? IEEE Transactions on Intelligent Transportation Systems, 22(11):6670–6681, 2021.
[11] Chen Wang, Yulu Dai, Wei Zhou, Yifei Geng, et al. A vision-based video crash detection framework for mixed traffic flow environment considering low-visibility condition. Journal of advanced transportation, 2020, 2020.
[12] Shih-Chia Huang, Da-Wei Jaw, Quoc-Viet Hoang, and Trung-Hieu Le. 3fl-net: An efficient approach for improving performance of lightweight detectors in rainy weather conditions. IEEE Transactions on Intelligent Transportation Systems, 24(4):4293–4305, 2023.
[13] Chris H. Bahnsen and Thomas B. Moeslund. Rain removal in traffic surveil-lance: Does it matter? IEEE Transactions on Intelligent Transportation Systems, 20(8):2802–2819, 2019.
[14] Martin Hahner, Christos Sakaridis, Dengxin Dai, and Luc Van Gool. Fog simulation on real lidar point clouds for 3d object detection in adverse weather. In 2021 IEEE/CVF International Conference on Computer Vision (ICCV), pages 15263–15272, 2021.
[15] Kaihao Zhang, Rongqing Li, Yanjiang Yu, Wenhan Luo, and Changsheng Li. Deep dense multi-scale network for snow removal using semantic and depth priors. IEEE Transactions on Image Processing, 30:7419–7431, 2021.
[16] Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. Generative adversarial nets. In Advances in neural information processing systems, pages 2672–2680, 2014.
[17] Shih-Chia Huang, Da-Wei Jaw, Bo-Hao Chen, and Sy-Yen Kuo. Single image snow removal using sparse representation and particle swarm optimizer. ACM Trans. In-tell. Syst. Technol., 11(2), jan 2020.
[18] Shih-Chia Huang, Da-Wei Jaw, Bo-Hao Chen, and Sy-Yen Kuo. An efficient sin-gle image enhancement approach using luminance perception transformation. IEEE Transactions on Emerging Topics in Computing, 9(2):1083–1094, 2021.
[19] Xueyang Fu, Jiabin Huang, Xinghao Ding, Yinghao Liao, and John Paisley. Clear-ing the skies: A deep network architecture for single-image rain removal. IEEE Transactions on Image Processing, 26(6):2944–2956, 2017.
[20] Christian Szegedy, Sergey Ioffe, Vincent Vanhoucke, and Alexander A. Alemi. Inception-v4, inception-resnet and the impact of residual connections on learn-ing. In Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, AAAI’17, page 4278–4284. AAAI Press, 2017.
[21] Alessandro Carfì and Fulvio Mastrogiovanni. Gesture-based human-machine interaction: Taxonomy, problem definition, and analysis. IEEE Transactions on Cyber-netics, pages 1–17, 2021.
[22] Jiahui Yu, Hongwei Gao, Dalin Zhou, Jinguo Liu, Qing Gao, and Zhaojie Ju. Deep temporal model-based identity-aware hand detection for space human–robot inter-action. IEEE Transactions on Cybernetics, 52(12):13738–13751, 2022.
[23] Sajid Javed, Arif Mahmood, Jorge Dias, Lakmal Seneviratne, and Naoufel Werghi. Hierarchical spatiotemporal graph regularized discriminative correlation filter for visual object tracking. IEEE Transactions on Cybernetics, 52(11):12259–12274, 2022.
[24] Shunli Zhang, Wei Lu, Weiwei Xing, and Li Zhang. Learning scale-adaptive tight correlation filter for object tracking. IEEE Transactions on Cybernetics, 50(1):270–283, 2020.
[25] Trung-Hieu Le, Shih-Chia Huang, and Da-Wei Jaw. Cross-resolution feature fu-sion for fast hand detection in intelligent homecare systems. IEEE Sensors Journal, 19(12):4696–4704, 2019.
[26] Jiayang Xie, Chengxing Gao, Junfeng Wu, Zhiguo Shi, and Jiming Chen. Small low-contrast target detection: Data-driven spatiotemporal feature fusion and imple-mentation. IEEE transactions on cybernetics, 52(11):11847–11858, 2021.
[27] Chao Huang, Zehua Yang, Jie Wen, Yong Xu, Qiuping Jiang, Jian Yang, and Yaowei Wang. Self-supervision-augmented deep autoencoder for unsupervised vi-sual anomaly detection. IEEE Transactions on Cybernetics, 52(12):13834–13847, 2021.
[28] Shih-Chia Huang, Trung-Hieu Le, and Da-Wei Jaw. Dsnet: Joint semantic learning for object detection in inclement weather conditions. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(8):2623–2633, 2021.
[29] Ross Girshick, Jeff Donahue, Trevor Darrell, and Jitendra Malik. Rich feature hi-erarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 580–587, 2014.
[30] Ross Girshick. Fast r-cnn. In Proceedings of the IEEE international conference on computer vision, pages 1440–1448, 2015.
[31] Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in neural information processing systems, pages 91–99, 2015.
[32] Kaiming He, Georgia Gkioxari, Piotr Dollár, and Ross Girshick. Mask r-cnn. In Proceedings of the IEEE international conference on computer vision, pages 2961–2969, 2017.
[33] Tsung-Yi Lin, Piotr Dollár, Ross Girshick, Kaiming He, Bharath Hariharan, and Serge Belongie. Feature pyramid networks for object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 2117–2125, 2017.
[34] Joseph Redmon, Santosh Divvala, Ross Girshick, and Ali Farhadi. You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 779–788, 2016.
[35] Joseph Redmon and Ali Farhadi. Yolo9000: better, faster, stronger. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 7263–7271, 2017.
[36] Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, and Alexander C Berg. Ssd: Single shot multibox detector. In European conference on computer vision, pages 21–37. Springer, 2016.
[37] Siyuan Li, Iago Breno Araujo, Wenqi Ren, Zhangyang Wang, Eric K Tokuda, Roberto Hirata Junior, Roberto Cesar-Junior, Jiawan Zhang, Xiaojie Guo, and Xi-aochun Cao. Single image deraining: A comprehensive benchmark analysis. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 3838–3847, 2019.
[38] Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531, 2015.
[39] Fisher Yu, Wenqi Xian, Yingying Chen, Fangchen Liu, Mike Liao, Vashisht Madha-van, and Trevor Darrell. Bdd100k: A diverse driving video database with scalable annotation tooling. arXiv preprint arXiv:1805.04687, 2018.
[40] Andreas Geiger, Philip Lenz, Christoph Stiller, and Raquel Urtasun. Vision meets robotics: The kitti dataset. The International Journal of Robotics Research, 32(11):1231–1237, 2013.
[41] Marius Cordts, Mohamed Omran, Sebastian Ramos, Timo Rehfeld, Markus En-zweiler, Rodrigo Benenson, Uwe Franke, Stefan Roth, and Bernt Schiele. The cityscapes dataset for semantic urban scene understanding. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3213–3223, 2016.
[42] Li-Wei Kang, Chia-Wen Lin, and Yu-Hsiang Fu. Automatic single-image-based rain streaks removal via image decomposition. IEEE Transactions on Image Processing, 21(4):1742–1755, 2012.
[43] Yu Luo, Yong Xu, and Hui Ji. Removing rain from a single image via discriminative sparse coding. In 2015 IEEE International Conference on Computer Vision (ICCV), pages 3397–3405, 2015.
[44] Yu Li, Robby T. Tan, Xiaojie Guo, Jiangbo Lu, and Michael S. Brown. Rain streak removal using layer priors. In 2016 IEEE Conference on Computer Vision and Pat-tern Recognition (CVPR), pages 2736–2744, 2016.
[45] Yi-Lei Chen and Chiou-Ting Hsu. A generalized low-rank appearance model for spatio-temporally correlated rain streaks. In 2013 IEEE International Conference on Computer Vision, pages 1968–1975, 2013.
[46] Duan-Yu Chen, Chien-Cheng Chen, and Li-Wei Kang. Visual depth guided color image rain streaks removal using sparse coding. IEEE Transactions on Circuits and Systems for Video Technology, 24(8):1430–1455, 2014.
[47] Kaiming He, Jian Sun, and Xiaoou Tang. Single image haze removal using dark channel prior. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(12):2341–2353, 2011.
[48] Shih-Chia Huang, Jian-Hui Ye, and Bo-Hao Chen. An advanced single-image vis-ibility restoration algorithm for real-world hazy scenes. IEEE Transactions on In-dustrial Electronics, 62(5):2962–2972, 2015.
[49] Bo-Hao Chen, Shih-Chia Huang, and Fan-Chieh Cheng. A high-efficiency and high-speed gain intervention refinement filter for haze removal. Journal of Display Tech-nology, 12(7):753–759, 2016.
[50] Shih-Chia Huang, Da-Wei Jaw, Wenli Li, Zhihui Lu, Sy-Yen Kuo, Benjamin C. M. Fung, Bo-Hao Chen, and Thanisa Numnonda. Image dehazing in disproportionate haze distributions. IEEE Access, 9:44599–44609, 2021.
[51] Earl J McCartney. Optics of the atmosphere: scattering by molecules and particles. New York, 1976.
[52] Martin Arjovsky, Soumith Chintala, and Léon Bottou. Wasserstein generative ad-versarial networks. In Proceedings of the 34th International Conference on Machine Learning, volume 70, pages 214–223, 06–11 Aug 2017.
[53] Ishaan Gulrajani, Faruk Ahmed, Martin Arjovsky, Vincent Dumoulin, and Aaron C Courville. Improved training of wasserstein gans. In Advances in Neural Information Processing Systems, pages 5767–5777, 2017.
[54] Jasper RR Uijlings, Koen EA Van De Sande, Theo Gevers, and Arnold WM Smeul-ders. Selective search for object recognition. International journal of computer vision, 104(2):154–171, 2013.
[55] Sergey Ioffe and Christian Szegedy. Batch normalization: Accelerating deep net-work training by reducing internal covariate shift. In Proceedings of the 32nd In-ternational Conference on Machine Learning, ICML 2015, Lille, France, 6-11 July 2015, volume 37 of JMLR Workshop and Conference Proceedings, pages 448–456, 2015.
[56] Shih-Chia Huang, Quoc-Viet Hoang, and Trung-Hieu Le. Sfa-net: A selective features absorption network for object detection in rainy weather conditions. IEEE Transactions on Neural Networks and Learning Systems, 2022.
[57] Adriana Romero, Nicolas Ballas, Samira Ebrahimi Kahou, Antoine Chassang, Carlo Gatta, and Yoshua Bengio. Fitnets: Hints for thin deep nets. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, 2015.
[58] Sergey Zagoruyko and Nikos Komodakis. Paying more attention to attention: Im-proving the performance of convolutional neural networks via attention transfer. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings, 2017.
[59] Yuntao Chen, Naiyan Wang, and Zhaoxiang Zhang. Darkrank: Accelerating deep metric learning via cross sample similarities transfer. In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18), pages 2852–2859, 2018.
[60] Zehao Huang and Naiyan Wang. Like what you like: Knowledge distill via neuron selectivity transfer. CoRR, abs/1707.01219, 2017.
[61] Jonathan Long, Evan Shelhamer, and Trevor Darrell. Fully convolutional networks for semantic segmentation. In 2015 IEEE Conference on Computer Vision and Pat-tern Recognition (CVPR), pages 3431–3440, 2015.
[62] Tsung-Yi Lin, Piotr Dollár, Ross Girshick, Kaiming He, Bharath Hariharan, and Serge Belongie. Feature pyramid networks for object detection. In 2017 IEEE Con-ference on Computer Vision and Pattern Recognition (CVPR), pages 936–944, 2017.
[63] Olaf Ronneberger, Philipp Fischer, and Thomas Brox. U-net: Convolutional net-works for biomedical image segmentation. In Nassir Navab, Joachim Hornegger, William M. Wells, and Alejandro F. Frangi, editors, Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, pages 234–241, Cham, 2015. Springer International Publishing.
[64] Saining Xie, Ross Girshick, Piotr Dollár, Zhuowen Tu, and Kaiming He. Aggregated residual transformations for deep neural networks. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 5987–5995, 2017.
[65] Hengshuang Zhao, Jianping Shi, Xiaojuan Qi, Xiaogang Wang, and Jiaya Jia. Pyra-mid scene parsing network. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 6230–6239, 2017.
[66] Liang-Chieh Chen, George Papandreou, Florian Schroff, and Hartwig Adam. Rethinking atrous convolution for semantic image segmentation. CoRR, abs/ 1706.05587, 2017.
[67] Kaiming He, Georgia Gkioxari, Piotr Dollár, and Ross Girshick. Mask r-cnn. In 2017 IEEE International Conference on Computer Vision (ICCV), pages 2980–2988, 2017.
[68] Markus Braun, Sebastian Krebs, Fabian Flohr, and Dariu M Gavrila. The eu-rocity persons dataset: A novel benchmark for object detection. arXiv preprint arXiv:1805.07193, 2018.
[69] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Identity mappings in deep residual networks. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part IV 14, pages 630–645. Springer, 2016.
[70] Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, and Alan L. Yuille. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(4):834–848, 2018.
[71] Andrew L Maas, Awni Y Hannun, and Andrew Y Ng. Rectifier nonlinearities im-prove neural network acoustic models. In Proc. icml, volume 30, page 3, 2013.
[72] Tijmen Tieleman and Geoffrey Hinton. Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude. COURSERA: Neural networks for machine learning, 4(2):26–31, 2012.
[73] Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C Lawrence Zitnick. Microsoft coco: Common objects in context. In European conference on computer vision, pages 740–755. Springer, 2014.
[74] Andrey Ignatov, Nikolay Kobyshev, Radu Timofte, Kenneth Vanhoey, and Luc Van Gool. Dslr-quality photos on mobile devices with deep convolutional networks. In Proceedings of the IEEE International Conference on Computer Vision, pages 3277–3285, 2017.
[75] Chen Chen, Qifeng Chen, Jia Xu, and Vladlen Koltun. Learning to see in the dark. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 3291–3300, 2018.
[76] Yifan Jiang, Xinyu Gong, Ding Liu, Yu Cheng, Chen Fang, Xiaohui Shen, Jianchao Yang, Pan Zhou, and Zhangyang Wang. Enlightengan: Deep light enhancement without paired supervision. IEEE Transactions on Image Processing, 30:2340–2349, 2021.
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top