nach oben

International Journal of Computer Vision

Erschienen in:

11.08.2020

Unsupervised Domain Adaptation in the Wild via Disentangling Representation Learning

verfasst von: Haoliang Li, Renjie Wan, Shiqi Wang, Alex C. Kot

Erschienen in: International Journal of Computer Vision | Ausgabe 2/2021

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config

KI-gestützte Suche

Aus

Abstract

Most recently proposed unsupervised domain adaptation algorithms attempt to learn domain invariant features by confusing a domain classifier through adversarial training. In this paper, we argue that this may not be an optimal solution in the real-world setting (a.k.a. in the wild) as the difference in terms of label information between domains has been largely ignored. As labeled instances are not available in the target domain in unsupervised domain adaptation tasks, it is difficult to explicitly capture the label difference between domains. To address this issue, we propose to learn a disentangled latent representation based on implicit autoencoders. In particular, a latent representation is disentangled into a global code and a local code. The global code is capturing category information via an encoder with a prior, and the local code is transferable across domains, which captures the “style” related information via an implicit decoder. Experimental results on digit recognition, object recognition and semantic segmentation demonstrate the effectiveness of our proposed method.

Nächster Artikel Volume Sweeping: Learning Photoconsistency for Multi-View Shape Reconstruction

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

Jetzt informieren

We omit other baseline methods under this setting as they can be categorized into the aforementioned baselines and achieved poorer performance.

We adopt the LeNet as backbone network, which is the benchmark for MNIST and USPS datasets.

Ben-David, S., Blitzer, J., Crammer, K., Kulesza, A., Pereira, F., & Vaughan, J. W. (2010). A theory of learning from different domains. Machine Learning, 79(1–2), 151–175.MathSciNetCrossRef

Benford, F. (1938). The law of anomalous numbers. Proceedings of the American Philosophical Society, 78(4), 551–572.MATH

Bousmalis, K., Silberman, N., Dohan, D., Erhan, D., & Krishnan, D. (2017). Unsupervised pixel-level domain adaptation with generative adversarial networks. In CVPR.

Cao, Z., You, K., Long, M., Wang, J., & Yang, Q. (2019). Learning to transfer examples for partial domain adaptation. In CVPR.

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

Chen, Y., Li, W., & Van Gool, L. (2018). Road: Reality oriented adaptation for semantic segmentation of urban scenes. In CVPR.

Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., et al. (2016). The cityscapes dataset for semantic urban scene understanding. In CVPR.

Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In CVPR.

French, G., Mackiewicz, M., & Fisher, M. (2017). Self-ensembling for visual domain adaptation. arXiv preprint arXiv:1706.05208.

Ganin, Y., Ustinova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., et al. (2016). Domain-adversarial training of neural networks. Journal of Machine Learning Research, 17, 2096–2030.MathSciNetMATH

Ghifary, M., Kleijn, W. B., Zhang, M., Balduzzi, D., & Li, W. (2016). Deep reconstruction-classification networks for unsupervised domain adaptation. In ECCV.

Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., et al. (2014). Generative adversarial nets. In NeurIPS.

Haeusser, P., Frerix, T., Mordvintsev, A., & Cremers, D. (2017). Associative domain adaptation. In CVPR.

Hendrycks, Da., & Dietterich, T. (2019). Benchmarking neural network robustness to common corruptions and perturbations. In ICLR.

Hoffman, J., Tzeng, E., Park, T., Zhu, J.-Y., Isola, P., Saenko, K., et al. (2018). Cycada: Cycle-consistent adversarial domain adaptation. In ICML.

Hoffman, J., Wang, D., Yu, F., & Darrell, T. (2016). Fcns in the wild: Pixel-level adversarial and constraint-based adaptation. arXiv preprint arXiv:1612.02649.

Huang, J., Gretton, A., Borgwardt, K. M., Schölkopf, B., & Smola, A. J. (2006). Correcting sample selection bias by unlabeled data. In NeurIPS.

Huang, X., Liu, M.-Y., Belongie, S., & Kautz, J. (2018). Multimodal unsupervised image-to-image translation. arXiv preprint arXiv:1804.04732.

Hull, J. J. (1994). A database for handwritten text recognition research. In PAMI.

Isola, P., Zhu, J.-Y., Zhou, T., & Efros, A. A. (2017). Image-to-image translation with conditional adversarial networks. arXiv preprint.

Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.

Kingma, D. P., & Welling, M. (2013). Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114.

Krizhevsky, A., & Hinton, G. (2009). Learning multiple layers of features from tiny images.

Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. In NeurIPS.

LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278–2324.CrossRef

Levinkov, E., & Fritz, M. (2013). Sequential Bayesian model update under structured scene prior for semantic road scenes labeling. In CVPR.

Lin, G., Milan, A., Shen, C., & Reid, I. (2017). Proceedings of the IEEE conference on computer vision and pattern recognition.

Liu, M.-Y., Breuel, T., & Kautz, J. (2017). Unsupervised image-to-image translation networks. In NeurIPS.

Liu, M.-Y., & Tuzel, O. (2016). Coupled generative adversarial networks. In NeurIPS.

Liu, Y.-C., Yeh, Y.-Y., Fu, T.-C., Wang, S.-D., Chiu, W.-C., & Wang, Y.-C. F. (2018). Detach and adapt: Learning cross-domain disentangled deep representation. In CVPR.

Long, M., Cao, Y., Wang, J., & Jordan, M. (2015). Learning transferable features with deep adaptation networks. In ICML.

Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In CVPR.

Long, M., Zhu, H., Wang, J., & Jordan, M. I. (2016). Unsupervised domain adaptation with residual transfer networks. In NeurIPS.

Makhzani, A. (2018). Implicit autoencoders. arXiv preprint arXiv:1805.09804.

Makhzani, A., & Frey, B. J. (2017). Pixelgan autoencoders. In NeurIPS.

Makhzani, A., Shlens, J., Jaitly, N., Goodfellow, I., & Frey, B. (2015). Adversarial autoencoders. arXiv preprint arXiv:1511.05644.

Ming Harry Hsu, T., Yu Chen, W., Hou, C.-A., Hubert Tsai, Y.-H., Yeh, Y.-R., & Frank Wang, Y.-C. (2015). Unsupervised domain adaptation with imbalanced cross-domain data. In ICCV.

Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., & Ng, A. Y. (2011). Reading digits in natural images with unsupervised feature learning. In NeurIPS Workshop, volume 2011.

Ngiam, J., Khosla, A., Kim, M., Nam, J., Lee, H., & Ng, A. Y. (2011). Multimodal deep learning. In ICML.

Pan, S. J., Tsang, I. W., Kwok, J. T., & Yang, Q. (2011). Domain adaptation via transfer component analysis. In TNN.

Pan, S. J., & Yang, Q. (2010). A survey on transfer learning. In TKDE.

Pan, Y., Yao, T., Li, Y., Wang, Y., Ngo, C.-W., & Mei, T. (2019). Transferrable prototypical networks for unsupervised domain adaptation. In CVPR.

Richter, S. R., Vineet, V., Roth, S., & Koltun, V. (2016). Playing for data: Ground truth from computer games. In ECCV.

Ros, G., Sellart, L., Materzynska, J., Vazquez, D., & Lopez, A. M. (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 (pp. 3234–3243).

Russo, P., Carlucci, F. M., Tommasi, T., & Caputo, B. (2018). From source to target and back: Symmetric bi-directional adaptive gan. In CVPR.

Saito, K., Watanabe, K., Ushiku, Y., & Harada, T. (2018). Maximum classifier discrepancy for unsupervised domain adaptation. In CVPR.

Sankaranarayanan, S., Balaji, Y., Jain, A., Lim, S. N., & Chellappa, R. (2017). Unsupervised domain adaptation for semantic segmentation with gans. arXiv preprint arXiv:1711.06969.

Schölkopf, B., Janzing, D., Peters, J., Sgouritsa, E., Zhang, K., & Mooij, J. (2012). On causal and anticausal learning. In ICML.

Shrivastava, A., Pfister, T., Tuzel, O., Susskind, J., Wang, W., & Webb, R. (2017). Learning from simulated and unsupervised images through adversarial training. In CVPR, Vol. 2, p. 5.

Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.

Taigman, Y., Polyak, A., & Wolf, L. (2016). Unsupervised cross-domain image generation. arXiv preprint arXiv:1611.02200.

Tsai, Y.-H., Hung, W.-C., Schulter, S., Sohn, K., Yang, M.-H., & Chandraker, M. (2018). Learning to adapt structured output space for semantic segmentation. arXiv preprint arXiv:1802.10349.

Tzeng, E., Hoffman, J., Darrell, T., & Saenko, K. (2015). Simultaneous deep transfer across domains and tasks. In ICCV.

Tzeng, E., Hoffman, J., Saenko, K., & Darrell, T. (2017). Adversarial discriminative domain adaptation. In CVPR.

Vu, T.-H., Jain, H., Bucher, M., Cord, M., & Pérez, P. (2019). Advent: Adversarial entropy minimization for domain adaptation in semantic segmentation. In CVPR.

Wang, T.-C., Liu, M.-Y., Zhu, J.-Y., Tao, A., Kautz, J., & Catanzaro, B. (2017). High-resolution image synthesis and semantic manipulation with conditional gans. arXiv preprint arXiv:1711.11585.

Zagoruyko, S., & Komodakis, N. (2016). Wide residual networks. arXiv preprint arXiv:1605.07146.

Zhang, Y., David, P., & Gong, B. (2017). Curriculum domain adaptation for semantic segmentation of urban scenes. In ICCV.

Zhang, Y., Qiu, Z., Yao, T., Liu, D., & Mei, T. (2018). Fully convolutional adaptation networks for semantic segmentation. In CVPR.

Zhu, J.-Y., Park, T., Isola, P., & Efros, A. A. (2017). Unpaired image-to-image translation using cycle-consistent adversarial networks. arXiv preprint arXiv:1703.10593.

Titel: Unsupervised Domain Adaptation in the Wild via Disentangling Representation Learning
verfasst von: Haoliang Li
Renjie Wan
Shiqi Wang
Alex C. Kot
Publikationsdatum: 11.08.2020
Verlag: Springer US
Erschienen in: International Journal of Computer Vision / Ausgabe 2/2021
Print ISSN: 0920-5691
Elektronische ISSN: 1573-1405
DOI: https://doi.org/10.1007/s11263-020-01364-5

Springer Professional

Abstract

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Wirtschaft"

Springer Professional "Technik"

Weitere Artikel der Ausgabe 2/2021

Unsupervised Deep Representation Learning for Real-Time Tracking

JA-Net: Joint Facial Action Unit Detection and Face Alignment Via Adaptive Attention

Fine-Grained Instance-Level Sketch-Based Image Retrieval

Beyond Covariance: SICE and Kernel Based Visual Feature Representation

Rain Rendering for Evaluating and Improving Robustness to Bad Weather

Image Matching Across Wide Baselines: From Paper to Practice