publication . Preprint . 2016

FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation

Hoffman, Judy; Wang, Dequan; Yu, Fisher; Darrell, Trevor;
Open Access English
  • Published: 08 Dec 2016
Abstract
Fully convolutional models for dense prediction have proven successful for a wide range of visual tasks. Such models perform well in a supervised setting, but performance can be surprisingly poor under domain shifts that appear mild to a human observer. For example, training on one city and testing on another in a different geographic region and/or weather condition may result in significantly degraded performance due to pixel-level distribution shift. In this paper, we introduce the first domain adaptive semantic segmentation method, proposing an unsupervised adversarial approach to pixel prediction problems. Our method consists of both global and category spec...
Subjects
free text keywords: Computer Science - Computer Vision and Pattern Recognition
Download from
34 references, page 1 of 3

[1] L.-C. Chen, G. Papandreou, I. Kokkinos, K. Murphy, and A. L. Yuille. Semantic image segmentation with deep convolutional nets and fully connected crfs. In ICLR, 2015. 1, 2

[2] W. Chen, H. Wang, Y. Li, H. Su, D. Lischinsk, D. CohenOr, B. Chen, et al. Synthesizing training images for boosting human 3d pose estimation. In 3DV, 2016. 3

[3] M. Cordts, M. Omran, S. Ramos, T. Rehfeld, M. Enzweiler, R. Benenson, U. Franke, S. Roth, and B. Schiele. The cityscapes dataset for semantic urban scene understanding. In CVPR, 2016. 2, 5

[4] J. Dai, K. He, and J. Sun. Instance-aware semantic segmentation via multi-task network cascades. In CVPR, 2016. 1

[5] C. Farabet, C. Couprie, L. Najman, and Y. LeCun. Learning hierarchical features for scene labeling. TPAMI, 2013. 2

[6] Y. Ganin and V. Lempitsky. Unsupervised domain adaptation by backpropagation. In ICML, 2015. 2

[7] Y. Ganin, E. Ustinova, H. Ajakan, P. Germain, H. Larochelle, F. Laviolette, M. Marchand, and V. Lempitsky. Domainadversarial training of neural networks. JMLR, 2016. 2, 3

[8] B. Gong, Y. Shi, F. Sha, and K. Grauman. Geodesic flow kernel for unsupervised domain adaptation. In CVPR, 2012. 2

[9] I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio. Generative adversarial nets. In NIPS, 2014. 2

[10] B. Hariharan, P. Arbela´ez, R. Girshick, and J. Malik. Simultaneous detection and segmentation. In ECCV, 2014. 2

[11] J. Hoffman, S. Guadarrama, E. S. Tzeng, R. Hu, J. Donahue, R. Girshick, T. Darrell, and K. Saenko. Lsda: Large scale detection through adaptation. In NIPS, 2014. 2 [OpenAIRE]

[12] J. Hoffman, D. Pathak, T. Darrell, and K. Saenko. Detector discovery in the wild: Joint multiple instance and representation learning. In CVPR, 2015. 2

[13] J. Hoffman, D. Pathak, E. Tzeng, J. Long, S. Guadarrama, T. Darrell, and K. Saenko. Large scale visual recognition through adaptation using joint representation and multiple instance learning. JMLR, 2016. 2

[14] S. Hong, H. Noh, and B. Han. Decoupled deep neural network for semi-supervised semantic segmentation. In NIPS, 2015. 2

[15] S. Hong, J. Oh, B. Han, and H. Lee. Learning transferrable knowledge for semantic segmentation with deep convolutional neural network. In CVPR, 2016. 2

34 references, page 1 of 3
Abstract
Fully convolutional models for dense prediction have proven successful for a wide range of visual tasks. Such models perform well in a supervised setting, but performance can be surprisingly poor under domain shifts that appear mild to a human observer. For example, training on one city and testing on another in a different geographic region and/or weather condition may result in significantly degraded performance due to pixel-level distribution shift. In this paper, we introduce the first domain adaptive semantic segmentation method, proposing an unsupervised adversarial approach to pixel prediction problems. Our method consists of both global and category spec...
Subjects
free text keywords: Computer Science - Computer Vision and Pattern Recognition
Download from
34 references, page 1 of 3

[1] L.-C. Chen, G. Papandreou, I. Kokkinos, K. Murphy, and A. L. Yuille. Semantic image segmentation with deep convolutional nets and fully connected crfs. In ICLR, 2015. 1, 2

[2] W. Chen, H. Wang, Y. Li, H. Su, D. Lischinsk, D. CohenOr, B. Chen, et al. Synthesizing training images for boosting human 3d pose estimation. In 3DV, 2016. 3

[3] M. Cordts, M. Omran, S. Ramos, T. Rehfeld, M. Enzweiler, R. Benenson, U. Franke, S. Roth, and B. Schiele. The cityscapes dataset for semantic urban scene understanding. In CVPR, 2016. 2, 5

[4] J. Dai, K. He, and J. Sun. Instance-aware semantic segmentation via multi-task network cascades. In CVPR, 2016. 1

[5] C. Farabet, C. Couprie, L. Najman, and Y. LeCun. Learning hierarchical features for scene labeling. TPAMI, 2013. 2

[6] Y. Ganin and V. Lempitsky. Unsupervised domain adaptation by backpropagation. In ICML, 2015. 2

[7] Y. Ganin, E. Ustinova, H. Ajakan, P. Germain, H. Larochelle, F. Laviolette, M. Marchand, and V. Lempitsky. Domainadversarial training of neural networks. JMLR, 2016. 2, 3

[8] B. Gong, Y. Shi, F. Sha, and K. Grauman. Geodesic flow kernel for unsupervised domain adaptation. In CVPR, 2012. 2

[9] I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio. Generative adversarial nets. In NIPS, 2014. 2

[10] B. Hariharan, P. Arbela´ez, R. Girshick, and J. Malik. Simultaneous detection and segmentation. In ECCV, 2014. 2

[11] J. Hoffman, S. Guadarrama, E. S. Tzeng, R. Hu, J. Donahue, R. Girshick, T. Darrell, and K. Saenko. Lsda: Large scale detection through adaptation. In NIPS, 2014. 2 [OpenAIRE]

[12] J. Hoffman, D. Pathak, T. Darrell, and K. Saenko. Detector discovery in the wild: Joint multiple instance and representation learning. In CVPR, 2015. 2

[13] J. Hoffman, D. Pathak, E. Tzeng, J. Long, S. Guadarrama, T. Darrell, and K. Saenko. Large scale visual recognition through adaptation using joint representation and multiple instance learning. JMLR, 2016. 2

[14] S. Hong, H. Noh, and B. Han. Decoupled deep neural network for semi-supervised semantic segmentation. In NIPS, 2015. 2

[15] S. Hong, J. Oh, B. Han, and H. Lee. Learning transferrable knowledge for semantic segmentation with deep convolutional neural network. In CVPR, 2016. 2

34 references, page 1 of 3
Any information missing or wrong?Report an Issue