Article

Transferring GANs: Generating Images from Limited Data

Authors:

Joost van de Weijer,

Abel Gonzalez-Garcia,

Bogdan RaducanuAuthors Info & Claims

Computer Vision – ECCV 2018: 15th European Conference, Munich, Germany, September 8–14, 2018, Proceedings, Part VI

Pages 220 - 236

https://doi.org/10.1007/978-3-030-01231-1_14

Published: 08 September 2018 Publication History

Abstract

Transferring knowledge of pre-trained networks to new domains by means of fine-tuning is a widely used practice for applications based on discriminative models. To the best of our knowledge this practice has not been studied within the context of generative deep networks. Therefore, we study domain adaptation applied to image generation with generative adversarial networks. We evaluate several aspects of domain adaptation, including the impact of target domain size, the relative distance between source and target domain, and the initialization of conditional GANs. Our results show that using knowledge from pre-trained networks can shorten the convergence time and can significantly improve the quality of the generated images, especially when target data is limited. We show that these conclusions can also be drawn for conditional GANs even when the pre-trained model was trained without conditioning. Our results also suggest that density is more important than diversity and a dataset with one or few densely sampled classes is a better source model than more diverse datasets such as ImageNet or Places.

References

[1]

Arjovsky, M., Bottou, L.: Towards principled methods for training generative adversarial networks. In: ICLR (2017)

[2]

Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: ICML, pp. 214–223 (2017)

[3]

Azizpour H, Razavian AS, Sullivan J, Maki A, and Carlsson S Factors of transferability for a generic convnet representation IEEE Trans. PAMI 2016 38 9 1790-1802

[4]

Borji, A.: Pros and Cons of GAN evaluation measures. arXiv preprint arXiv:1802.03446 (2018)

[5]

Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., Abbeel, P.: Infogan: interpretable representation learning by information maximizing generative adversarial nets. In: NIPS (2016)

[6]

Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: CVPR, pp. 3213–3223 (2016)

[7]

Danihelka, I., Lakshminarayanan, B., Uria, B., Wierstra, D., Dayan, P.: Comparison of maximum likelihood and GAN-based training of real NVPs. arXiv preprint arXiv:1705.05263 (2017)

[8]

Denton, E.L., Chintala, S., Fergus, R., et al.: Deep generative image models using a Laplacian pyramid of adversarial networks. In: NIPS, pp. 1486–1494 (2015)

[9]

Donahue, J., et al.: DeCAF: a deep convolutional activation feature for generic visual recognition. In: ICML, pp. 647–655 (2014)

[10]

Dumoulin, V., et al.: Adversarially learned inference. In: ICLR (2017)

[11]

Dumoulin, V., Shlens, J., Kudlur, M.: A learned representation for artistic style. In: ICLR (2017)

[12]

Ganin Y et al. Domain-adversarial training of neural networks JMLR 2016 17 1 2030-2096

[13]

Goodfellow, I., et al.: Generative adversarial nets. In: NIPS, pp. 2672–2680 (2014)

[14]

Grinblat, G.L., Uzal, L.C., Granitto, P.M.: Class-splitting generative adversarial networks. arXiv preprint arXiv:1709.07359 (2017)

[15]

Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.C.: Improved training of Wasserstein GANs. In: NIPS, pp. 5769–5779 (2017)

[16]

He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)

[17]

Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Klambauer, G., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a Nash equilibrium. In: NIPS (2017)

[18]

Hu, J., Lu, J., Tan, Y.P.: Deep transfer metric learning. In: CVPR, pp. 325–333. IEEE (2015)

[19]

Huang, G.B., Mattar, M., Berg, T., Learned-Miller, E.: Labeled faces in the wild: a database for studying face recognition in unconstrained environments. In: Workshop on Faces in ‘Real-Life’ Images: Detection, Alignment, and Recognition (2008)

[20]

Huang, X., Li, Y., Poursaeed, O., Hopcroft, J., Belongie, S.: Stacked generative adversarial networks. In: CVPR, vol. 2, p. 4 (2017)

[21]

Im, D.J., Ma, H., Taylor, G., Branson, K.: Quantitatively evaluating GANs with divergences proposed for training. In: ICLR (2018)

[22]

Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. In: ICLR (2018)

[23]

Kim, T., Cha, M., Kim, H., Lee, J., Kim, J.: Learning to discover cross-domain relations with generative adversarial networks. In: ICML, pp. 1857–1865 (2017)

[24]

Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2014)

[25]

Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: NIPS, pp. 1097–1105 (2012)

[26]

Ledig, C., et al.: Photo-realistic single image super-resolution using a generative adversarial network. In: CVPR (2016)

[27]

Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: ICCV, pp. 3730–3738 (2015)

[28]

Ma, L., Jia, X., Sun, Q., Schiele, B., Tuytelaars, T., Van Gool, L.: Pose guided person image generation. In: NIPS, pp. 405–415 (2017)

[29]

Mirza, M., Osindero, S.: Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784 (2014)

[30]

Miyato, T., Koyama, M.: CGANs with projection discriminator. In: ICLR (2018)

[31]

Nilsback, M.E., Zisserman, A.: Automated flower classification over a large number of classes. In: ICVGIP, pp. 722–729. IEEE (2008)

[32]

Odena, A., Olah, C., Shlens, J.: Conditional image synthesis with auxiliary classifier GANs. In: ICML (2016)

[33]

Oquab, M., Bottou, L., Laptev, I., Sivic, J.: Learning and transferring mid-level image representations using convolutional neural networks. In: CVPR, pp. 1717–1724. IEEE (2014)

[34]

Pan SJ and Yang Q A survey on transfer learning IEEE Trans. Knowl. Data Eng. 2010 22 10 1345-1359

[35]

Perarnau, G., van de Weijer, J., Raducanu, B., Álvarez, J.M.: Invertible conditional GANs for image editing. In: NIPS 2016 Workshop on Adversarial Training (2016)

[36]

Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. In: ICLR (2015)

[37]

Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., Lee, H.: Generative adversarial text to image synthesis. In: ICML, pp. 1060–1069 (2016)

[38]

Russakovsky O et al. Imagenet large scale visual recognition challenge IJCV 2015 115 3 211-252

[39]

Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. In: NIPS, pp. 2234–2242 (2016)

[40]

Smith, E., Meger, D.: Improved adversarial systems for 3D object generation and reconstruction. arXiv preprint arXiv:1707.09557 (2017)

[41]

Sricharan, K., Bala, R., Shreve, M., Ding, H., Saketh, K., Sun, J.: Semi-supervised conditional GANs. arXiv preprint arXiv:1708.05789 (2017)

[42]

Theis, L., van den Oord, A., Bethge, M.: A note on the evaluation of generative models. In: ICLR (2015)

[43]

Tzeng, E., Hoffman, J., Darrell, T., Saenko, K.: Simultaneous deep transfer across domains and tasks. In: CVPR, pp. 4068–4076 (2015)

[44]

Wang, Y., Zhang, L., van de Weijer, J.: Ensembles of generative adversarial networks. In: NIPS 2016 Workshop on Adversarial Training (2016)

[45]

Yu, F., Zhang, Y., Song, S., Seff, A., Xiao, J.: Construction of a large-scale image dataset using deep learning with humans in the loop. arXiv preprint arXiv:1506.03365 (2015)

[46]

Zhang, H., et al.: StackGAN: text to photo-realistic image synthesis with stacked generative adversarial networks. In: ICCV, pp. 5908–5916 (2017)

[47]

Zhang, Z., Song, Y., Qi, H.: Age progression/regression by conditional adversarial autoencoder. In: CVPR, vol. 2 (2017)

[48]

Zhou, B., Lapedriza, A., Xiao, J., Torralba, A., Oliva, A.: Learning deep features for scene recognition using places database. In: NIPS, pp. 487–495 (2014)

[49]

Zhou, Z., et al.: Activation maximization generative adversarial nets. In: ICLR (2018)

[50]

Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: ICCV, pp. 2242–2251 (2017)

Cited By

Wang XLin BLiu DChen YXu CSalakhutdinov RKolter ZHeller KWeller AOliver NScarlett JBerkenkamp F(2024)Bridging data gaps in diffusion models with adversarial noise-based transfer learningProceedings of the 41st International Conference on Machine Learning10.5555/3692070.3694158(50944-50959)Online publication date: 21-Jul-2024
https://dl.acm.org/doi/10.5555/3692070.3694158
Kim SNam JYu SShin YShin JSalakhutdinov RKolter ZHeller KWeller AOliver NScarlett JBerkenkamp F(2024)Data-efficient molecular generation with hierarchical textual inversionProceedings of the 41st International Conference on Machine Learning10.5555/3692070.3693048(24392-24414)Online publication date: 21-Jul-2024
https://dl.acm.org/doi/10.5555/3692070.3693048
Kong ZHu NHu YMeng JKoral YVallina-Rodríguez NSuarez-Tángil GLevin DPelsser C(2024)High-Fidelity Cellular Network Control-Plane Traffic Generation without Domain KnowledgeProceedings of the 2024 ACM on Internet Measurement Conference10.1145/3646547.3688422(530-544)Online publication date: 4-Nov-2024
https://dl.acm.org/doi/10.1145/3646547.3688422
Show More Cited By

Index Terms

Transferring GANs: Generating Images from Limited Data
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
  2. Machine learning
    1. Machine learning approaches
      1. Neural networks

Index terms have been assigned to the content through auto-classification.

Recommendations

GIU-GANs: Global Information Utilization for Generative Adversarial Networks
Abstract
Recently, with the rapid development of artificial intelligence, image generation based on deep learning has advanced significantly. Image generation based on Generative Adversarial Networks (GANs) is a promising study. However, because ...
Deep adversarial transition learning using cross-grafted generative stacks
Abstract
As a common approach of deep domain adaptation in computer vision, current works have mainly focused on learning domain-invariant features from different domains, achieving limited success in transfer learning. In this paper, we ...
Generative Adversarial Networks (GANs): Challenges, Solutions, and Future Directions

Generative Adversarial Networks (GANs) is a novel class of deep generative models that has recently gained significant attention. GANs learn complex and high-dimensional distributions implicitly over images, audio, and data. However, there exist major ...

Comments

Information & Contributors

Information

Published In

cover image Guide Proceedings

Computer Vision – ECCV 2018: 15th European Conference, Munich, Germany, September 8–14, 2018, Proceedings, Part VI

Sep 2018

724 pages

ISBN:978-3-030-01230-4

DOI:10.1007/978-3-030-01231-1

Editors:
Vittorio Ferrari
Google Research, Zurich, Switzerland
,
Martial Hebert
Carnegie Mellon University, Pittsburgh, PA, USA
,
Cristian Sminchisescu
Google Research, Zurich, Switzerland
,
Yair Weiss
Hebrew University of Jerusalem, Jerusalem, Israel

© Springer Nature Switzerland AG 2018.

Publisher

Springer-Verlag

Berlin, Heidelberg

Publication History

Published: 08 September 2018

Author Tags

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

11
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 04 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Wang XLin BLiu DChen YXu CSalakhutdinov RKolter ZHeller KWeller AOliver NScarlett JBerkenkamp F(2024)Bridging data gaps in diffusion models with adversarial noise-based transfer learningProceedings of the 41st International Conference on Machine Learning10.5555/3692070.3694158(50944-50959)Online publication date: 21-Jul-2024
https://dl.acm.org/doi/10.5555/3692070.3694158
Kim SNam JYu SShin YShin JSalakhutdinov RKolter ZHeller KWeller AOliver NScarlett JBerkenkamp F(2024)Data-efficient molecular generation with hierarchical textual inversionProceedings of the 41st International Conference on Machine Learning10.5555/3692070.3693048(24392-24414)Online publication date: 21-Jul-2024
https://dl.acm.org/doi/10.5555/3692070.3693048
Kong ZHu NHu YMeng JKoral YVallina-Rodríguez NSuarez-Tángil GLevin DPelsser C(2024)High-Fidelity Cellular Network Control-Plane Traffic Generation without Domain KnowledgeProceedings of the 2024 ACM on Internet Measurement Conference10.1145/3646547.3688422(530-544)Online publication date: 4-Nov-2024
https://dl.acm.org/doi/10.1145/3646547.3688422
Xia SHu XSun LLi Q(2024)RefineStyle: Dynamic Convolution Refinement for StyleGANPattern Recognition and Computer Vision10.1007/978-981-97-8692-3_30(422-436)Online publication date: 18-Oct-2024
https://dl.acm.org/doi/10.1007/978-981-97-8692-3_30
Jo HSahadewa MGazali WPark I(2024)Deterministic Synthesis of Defect Images Using Null OptimizationPattern Recognition10.1007/978-3-031-78172-8_13(190-205)Online publication date: 1-Dec-2024
https://dl.acm.org/doi/10.1007/978-3-031-78172-8_13
Ni YKoniusz POh ANaumann TGloberson ASaenko KHardt MLevine S(2023)NICEProceedings of the 37th International Conference on Neural Information Processing Systems10.5555/3666122.3666729(13773-13801)Online publication date: 10-Dec-2023
https://dl.acm.org/doi/10.5555/3666122.3666729
Garciarena USantana RMendiburu ASilva SPaquete L(2023)Analyzing the interplay between transferable GANs and gradient optimizersProceedings of the Companion Conference on Genetic and Evolutionary Computation10.1145/3583133.3596406(1777-1784)Online publication date: 15-Jul-2023
https://dl.acm.org/doi/10.1145/3583133.3596406
Li QSchott SChen D(2023)SolarDetector: Automatic Solar PV Array Identification using Big Satellite Imagery DataProceedings of the 8th ACM/IEEE Conference on Internet of Things Design and Implementation10.1145/3576842.3582384(117-129)Online publication date: 9-May-2023
https://dl.acm.org/doi/10.1145/3576842.3582384
Kim SKang KKim GBaek SCho S(2022)DynaGAN: Dynamic Few-shot Adaptation of GANs to Multiple DomainsSIGGRAPH Asia 2022 Conference Papers10.1145/3550469.3555416(1-8)Online publication date: 29-Nov-2022
https://dl.acm.org/doi/10.1145/3550469.3555416
Li ZWang CZheng HZhang JLi B(2022)FakeCLR: Exploring Contrastive Learning for Solving Latent Discontinuity in Data-Efficient GANsComputer Vision – ECCV 202210.1007/978-3-031-19784-0_35(598-615)Online publication date: 23-Oct-2022
https://dl.acm.org/doi/10.1007/978-3-031-19784-0_35
Show More Cited By

View Options

View options

Media

Figures

Other

Tables

View Table of Contents