link管理
链接快照平台
- 输入网页链接，自动生成快照
- 标签化管理网页链接
相关文章推荐
|
暴走的伤疤 · 在r语言中什么时候加单引号或者双引号 - ...· 2 月前 · |
|
|
有情有义的开水瓶 · 那些年，三星玩过的非主流操作系统· 3 月前 · |
|
|
快乐的水煮肉 · Tutorial 04b - Adding ...· 4 月前 · |
|
|
风度翩翩的钢笔 · Reactive ...· 5 月前 · |
|
|
帅气的面包 · 山东泰山足球俱乐部：青训双冠诠释“高度一体化 ...· 6 月前 · |
link管理
›
Source Data-free Unsupervised Domain Adaptation for Semantic Segmentation | Proceedings of the 29th
|
发呆的煎鸡蛋
6 月前 |
Source Data-free Unsupervised Domain Adaptation for Semantic Segmentation
Authors
:
Mucong
Ye
,
Jing
Zhang
,
Jinpeng
Ouyang
, and
Ding
Yuan
Authors Info & Claims
Mucong
Ye
,
Jing
Zhang
,
Jinpeng
Ouyang
, and
Ding
Yuan
Authors Info & Claims
October 2021
Pages
2233
-
2242
Abstract
Deep\footnote learning-based semantic segmentation methods require a huge amount of training images with pixel-level annotations. Unsupervised domain adaptation (UDA) for semantic segmentation enables transferring knowledge learned from the synthetic data (source domain) with low-cost annotations to the real images (target domain). However, current UDA methods mostly require full access to the source domain data for feasible adaptation, which limits their applications in real-world scenarios with privacy, storage, or transmission issues. To this end, this paper identifies and addresses a more practical but challenging problem of UDA for semantic segmentation, where access to the original source domain data is forbidden. In other words, only the pre-trained source model and unlabelled target domain data are available for adaptation. To tackle the problem, we propose to construct a set of source domain virtual data to mimic the source domain distribution by identifying the target domain high-confidence samples predicted by the pre-trained source model. Then by analyzing the data properties in the cross-domain semantic segmentation tasks, we propose an uncertainty and prior distribution-aware domain adaptation method to align the virtual source domain and the target domain with both adversarial learning and self-training strategies. Extensive experiments on three cross-domain semantic segmentation datasets with in-depth analyses verify the effectiveness of the proposed method.
References
[1]
Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, and Alan L Yuille. 2017. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE transactions on pattern analysis and machine intelligence, Vol. 40, 4 (2017), 834--848.
[2]
Minghao Chen, Hongyang Xue, and Deng Cai. 2019 b. Domain adaptation for semantic segmentation with maximum squares loss. In Proceedings of the IEEE International Conference on Computer Vision. 2090--2099.
[3]
Yun-Chun Chen, Yen-Yu Lin, Ming-Hsuan Yang, and Jia-Bin Huang. 2019 a. Crdoco: Pixel-level domain transfer with cross-domain consistency. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . 1791--1800.
[4]
Sungha Choi, Joanne T. Kim, and Jaegul Choo. 2020. Cars Can't Fly Up in the Sky: Improving Urban-Scene Segmentation via Height-Driven Attention Networks. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) .
[5]
Marius Cordts, Mohamed Omran, Sebastian Ramos, Timo Rehfeld, Markus Enzweiler, Rodrigo Benenson, Uwe Franke, Stefan Roth, and Bernt Schiele. 2016. The cityscapes dataset for semantic urban scene understanding. In Proceedings of the IEEE conference on computer vision and pattern recognition . 3213--3223.
[6]
MAR Freeman, MRE Dean, and IWF Hanham. 1965. The etiology and prevention of functional instability of the foot. The Journal of bone and joint surgery. British volume, Vol. 47, 4 (1965), 678--685.
[7]
Jun Fu, Jing Liu, Haijie Tian, Yong Li, Yongjun Bao, Zhiwei Fang, and Hanqing Lu. 2019. Dual attention network for scene segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 3146--3154.
[8]
Yarin Gal and Zoubin Ghahramani. 2015. Bayesian convolutional neural networks with Bernoulli approximate variational inference. arXiv preprint arXiv:1506.02158 (2015).
[9]
Yarin Gal and Zoubin Ghahramani. 2016. Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In international conference on machine learning . PMLR, 1050--1059.
[10]
Muhammad Ghifary, W Bastiaan Kleijn, Mengjie Zhang, David Balduzzi, and Wen Li. 2016. Deep reconstruction-classification networks for unsupervised domain adaptation. In European Conference on Computer Vision. Springer, 597--613.
[11]
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. 770--778.
[12]
Judy Hoffman, Eric Tzeng, Taesung Park, Jun-Yan Zhu, Phillip Isola, Kate Saenko, Alexei Efros, and Trevor Darrell. 2018. Cycada: Cycle-consistent adversarial domain adaptation. In International conference on machine learning. PMLR, 1989--1998.
[13]
Judy Hoffman, Dequan Wang, Fisher Yu, and Trevor Darrell. 2016. Fcns in the wild: Pixel-level adversarial and constraint-based adaptation. arXiv preprint arXiv:1612.02649 (2016).
[14]
Neil Houlsby, Ferenc Huszár, Zoubin Ghahramani, and Máté Lengyel. 2011. Bayesian active learning for classification and preference learning. arXiv preprint arXiv:1112.5745 (2011).
[15]
Alex Kendall and Yarin Gal. 2017. What uncertainties do we need in bayesian deep learning for computer vision? arXiv preprint arXiv:1703.04977 (2017).
[16]
Jogendra Nath Kundu, Naveen Venkat, R Venkatesh Babu, et almbox. 2020. Universal source-free domain adaptation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 4544--4553.
[17]
Rui Li, Qianfen Jiao, Wenming Cao, Hau-San Wong, and Si Wu. 2020. Model adaptation: Unsupervised domain adaptation without source data. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . 9641--9650.
[18]
Yunsheng Li, Lu Yuan, and Nuno Vasconcelos. 2019. Bidirectional learning for domain adaptation of semantic segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . 6936--6945.
[19]
Qing Lian, Fengmao Lv, Lixin Duan, and Boqing Gong. 2019. Constructing self-motivated pyramid curriculums for cross-domain semantic segmentation: A non-adversarial approach. In Proceedings of the IEEE International Conference on Computer Vision. 6758--6767.
[20]
Jian Liang, Dapeng Hu, and Jiashi Feng. 2020. Do we really need to access the source data? source hypothesis transfer for unsupervised domain adaptation. In International Conference on Machine Learning . PMLR, 6028--6039.
[21]
Mingyuan Liu, Dan Schonfeld, and Wei Tang. 2021 a. Exploit Visual Dependency Relations for Semantic Segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . 9726--9735.
[22]
Yuang Liu, Wei Zhang, and Jun Wang. 2021 b. Source-free domain adaptation for semantic segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . 1215--1224.
[23]
Mingsheng Long, Yue Cao, Jianmin Wang, and Michael Jordan. 2015. Learning transferable features with deep adaptation networks. In International conference on machine learning. PMLR, 97--105.
[24]
Yawei Luo, Ping Liu, Tao Guan, Junqing Yu, and Yi Yang. 2019. Significance-aware information bottleneck for domain adaptive semantic segmentation. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 6778--6787.
[25]
Ke Mei, Chuang Zhu, Jiaqi Zou, and Shanghang Zhang. 2020. Instance adaptive self-training for unsupervised domain adaptation. arXiv preprint arXiv:2008.12197 (2020).
[26]
Umberto Michieli, Matteo Biasetton, Gianluca Agresti, and Pietro Zanuttigh. 2020. Adversarial learning and self-teaching techniques for domain adaptation in semantic segmentation. IEEE Transactions on Intelligent Vehicles, Vol. 5, 3 (2020), 508--518.
[27]
Saeid Motiian, Marco Piccirilli, Donald A Adjeroh, and Gianfranco Doretto. 2017. Unified deep supervised domain adaptation and generalization. In Proceedings of the IEEE international conference on computer vision. 5715--5725.
[28]
Subhabrata Mukherjee and Ahmed Hassan Awadallah. 2020. Uncertainty-aware Self-training for Text Classification with Few Labels. arXiv preprint arXiv:2006.15315 (2020).
[29]
Yuval Nirkin, Lior Wolf, and Tal Hassner. 2021. Hyperseg: Patch-wise hypernetwork for real-time semantic segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . 4061--4070.
[30]
Yassine Ouali, Céline Hudelot, and Myriam Tami. 2020. Semi-supervised semantic segmentation with cross-consistency training. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . 12674--12684.
[31]
Fei Pan, Inkyu Shin, Francois Rameau, Seokju Lee, and In So Kweon. 2020. Unsupervised intra-domain adaptation for semantic segmentation through self-supervision. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 3764--3773.
[32]
Yingwei Pan, Ting Yao, Yehao Li, Yu Wang, Chong-Wah Ngo, and Tao Mei. 2019. Transferrable prototypical networks for unsupervised domain adaptation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . 2239--2247.
[33]
Yanwei Pang, Yazhao Li, Jianbing Shen, and Ling Shao. 2019. Towards bridging semantic gap to improve semantic segmentation. In Proceedings of the IEEE/CVF International Conference on Computer Vision. 4230--4239.
[34]
Stephan R Richter, Vibhav Vineet, Stefan Roth, and Vladlen Koltun. 2016. Playing for data: Ground truth from computer games. In European conference on computer vision. Springer, 102--118.
[35]
German Ros, Laura Sellart, Joanna Materzynska, David Vazquez, and Antonio M Lopez. 2016. The synthia dataset: A large collection of synthetic images for semantic segmentation of urban scenes. In Proceedings of the IEEE conference on computer vision and pattern recognition. 3234--3243.
[36]
Kuniaki Saito, Yoshitaka Ushiku, and Tatsuya Harada. 2017. Asymmetric tri-training for unsupervised domain adaptation. In International Conference on Machine Learning. PMLR, 2988--2997.
[37]
Swami Sankaranarayanan, Yogesh Balaji, Arpit Jain, Ser Nam Lim, and Rama Chellappa. 2018. Learning from synthetic data: Addressing domain shift for semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . 3752--3761.
[38]
Ozan Sener, Hyun Oh Song, Ashutosh Saxena, and Silvio Savarese. 2016. Learning transferrable representations for unsupervised domain adaptation. In Proceedings of the 30th International Conference on Neural Information Processing Systems . 2118--2126.
[39]
Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. 2014. Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research, Vol. 15, 1 (2014), 1929--1958.
[40]
Jiayi Tian, Jing Zhang, Wen Li, and Dong Xu. 2021. VDM-DA: Virtual Domain Modeling for Source Data-free Domain Adaptation. arXiv preprint arXiv:2103.14357 (2021).
[41]
Marco Toldo, Umberto Michieli, Gianluca Agresti, and Pietro Zanuttigh. 2020. Unsupervised domain adaptation for mobile semantic segmentation based on cycle consistency and feature alignment. Image and Vision Computing, Vol. 95 (2020), 103889.
[42]
Yi-Hsuan Tsai, Wei-Chih Hung, Samuel Schulter, Kihyuk Sohn, Ming-Hsuan Yang, and Manmohan Chandraker. 2018. Learning to adapt structured output space for semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition . 7472--7481.
[43]
Tuan-Hung Vu, Himalaya Jain, Maxime Bucher, Matthieu Cord, and Patrick Pérez. 2019. Advent: Adversarial entropy minimization for domain adaptation in semantic segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2517--2526.
[44]
Li Wang, Dong Li, Yousong Zhu, Lu Tian, and Yi Shan. 2020 a. Dual super-resolution learning for semantic segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . 3774--3783.
[45]
Zhonghao Wang, Mo Yu, Yunchao Wei, Rogerio Feris, Jinjun Xiong, Wen-mei Hwu, Thomas S Huang, and Honghui Shi. 2020 b. Differential treatment for stuff and things: A simple unsupervised domain adaptation method for semantic segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 12635--12644.
[46]
Magnus Wrenninge and Jonas Unger. 2018. Synscapes: A photorealistic synthetic dataset for street scene parsing. arXiv preprint arXiv:1810.08705 (2018).
[47]
Yanchao Yang and Stefano Soatto. 2020. Fda: Fourier domain adaptation for semantic segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . 4085--4095.
[48]
Mucong Ye, Jingpeng Ouyang, Ge Chen, Jing Zhang, and Xiaogang Yu. 2021. Enhanced Feature Pyramid Network for Semantic Segmentation. In 2020 25th International Conference on Pattern Recognition (ICPR). IEEE, 3209--3216.
[49]
Changqian Yu, Jingbo Wang, Changxin Gao, Gang Yu, Chunhua Shen, and Nong Sang. 2020. Context prior for scene segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 12416--12425.
[50]
Jing Zhang, Zewei Ding, Wanqing Li, and Philip Ogunbona. 2018. Importance weighted adversarial nets for partial domain adaptation. In Proceedings of the IEEE conference on computer vision and pattern recognition . 8156--8164.
[51]
Jing Zhang, Wanqing Li, and Philip Ogunbona. 2017b. Joint geometrical and statistical alignment for visual domain adaptation. In Proceedings of the IEEE conference on computer vision and pattern recognition . 1859--1867.
[52]
Jing Zhang, Wanqing Li, and Philip Ogunbona. 2019 a. Unsupervised domain adaptation: A multi-task learning-based method. Knowledge-Based Systems, Vol. 186 (2019), 104975.
[53]
Jing Zhang, Wanqing Li, Philip Ogunbona, and Dong Xu. 2019 b. Recent advances in transfer learning for cross-dataset visual recognition: A problem-oriented perspective. ACM Computing Surveys (CSUR), Vol. 52, 1 (2019), 1--38.
[54]
Qiming Zhang, Jing Zhang, Wei Liu, and Dacheng Tao. 2019 c. Category anchor-guided unsupervised domain adaptation for semantic segmentation. arXiv preprint arXiv:1910.13049 (2019).
[55]
Yang Zhang, Philip David, and Boqing Gong. 2017a. Curriculum domain adaptation for semantic segmentation of urban scenes. In Proceedings of the IEEE international conference on computer vision . 2020--2030.
[56]
Zhedong Zheng and Yi Yang. 2019. Unsupervised scene adaptation with memory regularization in vivo. arXiv preprint arXiv:1912.11164 (2019).
[57]
Zhedong Zheng and Yi Yang. 2021. Rectifying pseudo label learning via uncertainty estimation for domain adaptive semantic segmentation. International Journal of Computer Vision, Vol. 129, 4 (2021), 1106--1120.
[58]
Qianyu Zhou, Zhengyang Feng, Guangliang Cheng, Xin Tan, Jianping Shi, and Lizhuang Ma. 2020. Uncertainty-Aware Consistency Regularization for Cross-Domain Semantic Segmentation. arXiv preprint arXiv:2004.08878 (2020).
[59]
Yang Zou, Zhiding Yu, BVK Kumar, and Jinsong Wang. 2018. Unsupervised domain adaptation for semantic segmentation via class-balanced self-training. In Proceedings of the European conference on computer vision (ECCV). 289--305.
[60]
Yang Zou, Zhiding Yu, Xiaofeng Liu, BVK Kumar, and Jinsong Wang. 2019. Confidence regularized self-training. In Proceedings of the IEEE International Conference on Computer Vision. 5982--5991.
Cited By
View all- Li G Ma X Wang Z Li H Zhang Q Wu C El Saddik A Mei T Cucchiara R Bertini M Tobon Vallejo D Atrey P Hossain M (2023) When Masked Image Modeling Meets Source-free Unsupervised Domain Adaptation: Dual-Level Masked Network for Semantic Segmentation Proceedings of the 31st ACM International Conference on Multimedia 10.1145/3581783.3612521 (7638-7647) Online publication date: 26-Oct-2023
- Kong X Jiang W Jia J Shi Y Xu R Liu S El Saddik A Mei T Cucchiara R Bertini M Tobon Vallejo D Atrey P Hossain M (2023) DUSA: Decoupled Unsupervised Sim2Real Adaptation for Vehicle-to-Everything Collaborative Perception Proceedings of the 31st ACM International Conference on Multimedia 10.1145/3581783.3611948 (1943-1954) Online publication date: 26-Oct-2023
- Wang Z Luo Y Chen Z Wang S Huang Z El Saddik A Mei T Cucchiara R Bertini M Tobon Vallejo D Atrey P Hossain M (2023) Cal-SFDA: Source-Free Domain-adaptive Semantic Segmentation with Differentiable Expected Calibration Error Proceedings of the 31st ACM International Conference on Multimedia 10.1145/3581783.3611808 (1167-1178) Online publication date: 26-Oct-2023
- Show More Cited By
-
An unsupervised domain adaptation brain CT segmentation method across image modalities and diseases
AbstractComputed tomography (CT) is the primary diagnostic tool for brain diseases. To determine the appropriate treatment plan, it is necessary to ascertain the patient’s bleeding volume. Automatic segmentation algorithms for hemorrhagic ...
Highlights- Solve unsupervised segmentation problem in a novel domain adaptation way.
- ...
-
Semantic Segmentation in Aerial Images Using Class-Aware Unsupervised Domain Adaptation
GEOAI '21: Proceedings of the 4th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge DiscoverySemantic segmentation using deep neural networks is an important component of aerial image understanding. However, models trained using data from one domain may not generalize well to another domain due to a domain shift between data distributions in ...
-
Union-Set Multi-source Model Adaptation for Semantic Segmentation
Computer Vision – ECCV 2022AbstractThis paper solves a generalized version of the problem of multi-source model adaptation for semantic segmentation. Model adaptation is proposed as a new domain adaptation problem which requires access to a pre-trained model instead of data for the ...
MM '21: Proceedings of the 29th ACM International Conference on Multimedia
October 2021
5796 pages
ISBN:
9781450386517
DOI:
10.1145/3474085
- General Chairs:
-
Heng Tao Shen
University of Electronic Science&Technology of China, China
, -
Yueting Zhuang
Zhejiang University, China
, -
John R. Smith
IBM, USA
, - Program Chairs:
-
Yang Yang
University of Electronic Science and Technology of China, China
, -
Pablo Cesar
CWI&TU Delft, The Netherlands
, -
Florian Metze
FACEBOOK, Inc., USA
, -
Balakrishnan Prabhakaran
University of Texas at Dallas, USA
-
View Citations8Total Citations
-
722Total Downloads
- Downloads (Last 12 months) 142
- Downloads (Last 6 weeks) 9
Other Metrics
Citations
Cited By
View all- Li G Ma X Wang Z Li H Zhang Q Wu C El Saddik A Mei T Cucchiara R Bertini M Tobon Vallejo D Atrey P Hossain M (2023) When Masked Image Modeling Meets Source-free Unsupervised Domain Adaptation: Dual-Level Masked Network for Semantic Segmentation Proceedings of the 31st ACM International Conference on Multimedia 10.1145/3581783.3612521 (7638-7647) Online publication date: 26-Oct-2023
- Kong X Jiang W Jia J Shi Y Xu R Liu S El Saddik A Mei T Cucchiara R Bertini M Tobon Vallejo D Atrey P Hossain M (2023) DUSA: Decoupled Unsupervised Sim2Real Adaptation for Vehicle-to-Everything Collaborative Perception Proceedings of the 31st ACM International Conference on Multimedia 10.1145/3581783.3611948 (1943-1954) Online publication date: 26-Oct-2023
- Wang Z Luo Y Chen Z Wang S Huang Z El Saddik A Mei T Cucchiara R Bertini M Tobon Vallejo D Atrey P Hossain M (2023) Cal-SFDA: Source-Free Domain-adaptive Semantic Segmentation with Differentiable Expected Calibration Error Proceedings of the 31st ACM International Conference on Multimedia 10.1145/3581783.3611808 (1167-1178) Online publication date: 26-Oct-2023
- Liu X Xing F El Fakhri G Woo J (2023) Memory consistent unsupervised off-the-shelf model adaptation for source-relaxed medical image segmentation Medical Image Analysis 10.1016/j.media.2022.102641 83 (102641) Online publication date: Jan-2023
- Ye Y Liu Z Zhang Y Li J Shen H Magalhães J del Bimbo A Satoh S Sebe N Alameda-Pineda X Jin Q Oria V Toni L (2022) Alleviating Style Sensitivity then Adapting Proceedings of the 30th ACM International Conference on Multimedia 10.1145/3503161.3548426 (1935-1944) Online publication date: 10-Oct-2022
- Yuan J Ma X Chen D Kuang K Wu F Lin L Magalhães J del Bimbo A Satoh S Sebe N Alameda-Pineda X Jin Q Oria V Toni L (2022) Label-Efficient Domain Generalization via Collaborative Exploration and Generalization Proceedings of the 30th ACM International Conference on Multimedia 10.1145/3503161.3548059 (2361-2370) Online publication date: 10-Oct-2022
- Yin N Shen L Li B Wang M Luo X Chen C Luo Z Hua X Magalhães J del Bimbo A Satoh S Sebe N Alameda-Pineda X Jin Q Oria V Toni L (2022) DEAL: An Unsupervised Domain Adaptive Framework for Graph-level Classification Proceedings of the 30th ACM International Conference on Multimedia 10.1145/3503161.3548012 (3470-3479) Online publication date: 10-Oct-2022
- Luo X Chen W Li C Zhou B Tan Y (2022) Multi-Level Consistency Learning for Source-Free Model Adaptation IEEE Robotics and Automation Letters 10.1109/LRA.2022.3216997 7 :4 (12419-12426) Online publication date: Oct-2022
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
Media
Figures
Other
Tables
Share
Share
Affiliations
Mucong
Ye
Beihang University, Beijing, China
Jing
Zhang
Beihang University, Beijing, China
Jinpeng
Ouyang
Beihang University, Beijing, China
Ding
Yuan
Beihang University, Beijing, China
Export Citations
Your Search Results Download Request
We are preparing your search results for download ...
We will inform you here when the file is ready.
Download now!
Your Search Results Download Request
Your file of search results citations is now ready.
Download now!
Your Search Results Download Request
Your search export query has expired. Please try again.
推荐文章
|
|
暴走的伤疤 · 在r语言中什么时候加单引号或者双引号 - CSDN文库 2 月前 |
|
|
有情有义的开水瓶 · 那些年，三星玩过的非主流操作系统 3 月前 |