Confidence Measures for Deep Learning in Domain Adaptation
Source abstract
Abstract
In recent years, Deep Neural Networks (DNNs) have led to impressive results in a wide variety of machine learning tasks, typically relying on the existence of a huge amount of supervised data. However, in many applications (e.g., bio–medical image analysis), gathering large sets of labeled data can be very difficult and costly. Unsupervised domain adaptation exploits data from a source domain, where annotations are available, to train a model able to generalize also to a target domain, where labels are unavailable. Recent research has shown that Generative Adversarial Networks (GANs) can be successfully employed for domain adaptation, although deciding when to stop learning is a major concern for GANs. In this work, we propose some confidence measures that can be used to early stop the GAN training, also showing how such measures can be employed to predict the reliability of the network output. The effectiveness of the proposed approach has been tested in two domain adaptation tasks, with very promising results.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Domain Adaptation and Few-Shot Learning · Machine Learning and Data Classification · Anomaly Detection Techniques and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Information Engineering and Mathematics, University of Siena, 53100 Siena, Italy
Department of Computer Science, University of Copenhagen, 2100 Copenhagen, Denmark
Cerebriu A/S, 2100 Copenhagen, Denmark
References (57)
Show source-provided references
1. Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014, January 23–28). Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.10.1109/CVPR.2014.81 ↗
2. Long, J., Shelhamer, E., and Darrell, T. (2015, January 7–12). Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.10.1109/CVPR.2015.7298965 ↗
3. Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., and Yuille, A.L. (2014). Semantic image segmentation with deep convolutional nets and fully connected CRFs. arXiv.
4. Amodei, D., Ananthanarayanan, S., Anubhai, R., Bai, J., Battenberg, E., Case, C., Casper, J., Catanzaro, B., Cheng, Q., and Chen, G. (2016, January 19–24). Deep speech 2: End–to–end speech recognition in English and Mandarin. Proceedings of the International Conference on Machine Learning, New York, NY, USA.
5. Caruana, R., Lou, Y., Gehrke, J., Koch, P., Sturm, M., and Elhadad, N. (2015, January 10–13). Intelligible models for healthcare: Predicting pneumonia risk and hospital 30-day readmission. Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Sydney, NSW, Australia.10.1145/2783258.2788613 ↗
6. Andreini, P., Bonechi, S., Bianchini, M., Mecocci, A., and Scarselli, F. (2018, January 4–7). A Deep Learning Approach to Bacterial Colony Segmentation. Proceedings of the International Conference on Artificial Neural Networks, Rhodes, Greece.10.1007/978-3-030-01424-7_51 ↗
7. Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., and Fei-Fei, L. (2009, January 20–25). Imagenet: A large–scale hierarchical image database. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.10.1109/CVPR.2009.5206848 ↗
8. Gretton, A., Smola, A.J., Huang, J., Schmittfull, M., Borgwardt, K.M., and Schölkopf, B. (2009). Covariate Shift by Kernel Mean Matching, MIT Press.10.7551/mitpress/9780262170055.003.0008 ↗
9. Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., and Darrell, T. (2014, January 21–26). Decaf: A deep convolutional activation feature for generic visual recognition. Proceedings of the International Conference on Machine Learning, Beijing, China.
10. Torralba, A., and Efros, A.A. (2011, January 20–25). Unbiased look at dataset bias. Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Colorado Springs, CO, USA.10.1109/CVPR.2011.5995347 ↗
11. Ben-David, S., Blitzer, J., Crammer, K., and Pereira, F. (2007). Analysis of representations for domain adaptation. Advances in Neural Information Processing Systems, MIT Press.10.7551/mitpress/7503.003.0022 ↗
12. Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014). Generative adversarial nets. Advances in Neural Information Processing Systems, MIT Press.
13. Volpi, R., Morerio, P., Savarese, S., and Murino, V. (2018, January 18–22). Adversarial feature augmentation for unsupervised domain adaptation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.10.1109/CVPR.2018.00576 ↗
14. Smith, L., and Gal, Y. (2018). Understanding Measures of Uncertainty for Adversarial Example Detection. arXiv.
15. Reading digits in natural images with unsupervised feature learning
16. Gradient-based learning applied to document recognition10.1109/5.726791 ↗
17. Krizhevsky, A., and Hinton, G. (2009). Learning Multiple Layers of Features from Tiny Images, University of Toronto. Technical report.
18. Coates, A., Ng, A., and Lee, H. (2011, January 11–13). An analysis of single–layer networks in unsupervised feature learning. Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, Fort Lauderdale, FL, USA.
19. Saenko, K., Kulis, B., Fritz, M., and Darrell, T. (2010, January 5–11). Adapting visual category models to new domains. Proceedings of the European Conference on Computer Vision, Crete, Greece.10.1007/978-3-642-15561-1_16 ↗
20. Jhuo, I.H., Liu, D., Lee, D., and Chang, S.F. (2012, January 16–21). Robust visual domain adaptation with low–rank reconstruction. Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI, USA.
21. Hoffman, J., Rodner, E., Donahue, J., Darrell, T., and Saenko, K. (2013). Efficient learning of domain–invariant image representations. arXiv.
22. Sun, B., and Saenko, K. (2016, January 8–16). Deep coral: Correlation alignment for deep domain adaptation. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.10.1007/978-3-319-49409-8_35 ↗
23. Long, M., Cao, Y., Wang, J., and Jordan, M.I. (2015). Learning transferable features with deep adaptation networks. arXiv.
24. Long, M., Zhu, H., Wang, J., and Jordan, M.I. (2016). Unsupervised domain adaptation with residual transfer networks. Advances in Neural Information Processing Systems, NIPS.
25. Haeusser, P., Frerix, T., Mordvintsev, A., and Cremers, D. (2017, January 22–27). Associative domain adaptation. Proceedings of the International Conference on Computer Vision (ICCV), Italy, France.10.1109/ICCV.2017.301 ↗
26. Luo, Z., Zou, Y., Hoffman, J., and Fei-Fei, L.F. (2017). Label efficient learning of transferable representations acrosss domains and tasks. Advances in Neural Information Processing Systems, NIPS.
27. Domain-adversarial training of neural networks
28. Tzeng, E., Hoffman, J., Darrell, T., and Saenko, K. (2015, January 7–13). Simultaneous deep transfer across domains and tasks. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.10.1109/ICCV.2015.463 ↗
29. Ganin, Y., and Lempitsky, V. (2015, January 6–11). Unsupervised domain adaptation by backpropagation. Proceedings of the 32nd International Conference on Machine Learning, Lille, France.
30. Tzeng, E., Hoffman, J., Saenko, K., and Darrell, T. (2017, January 21–26). Adversarial discriminative domain adaptation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.316 ↗
31. Damodaran, B.B., Kellenberger, B., Flamary, R., Tuia, D., and Courty, N. (2018, January 8–14). DeepJDOT: Deep Joint distribution optimal transport for unsupervised domain adaptation. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01225-0_28 ↗
32. Shu, R., Bui, H., Narui, H., and Ermon, S. (May, January 30). A DIRT–T Approach to Unsupervised Domain Adaptation. Proceedings of the International Conference on Learning Representations, Vancouver, BC, Canada.
33. Taigman, Y., Polyak, A., and Wolf, L. (2017, January 24–26). Unsupervised cross-domain image generation. Proceedings of the International Conference on Learning Representations (ICLR), Toulon, France.
34. Liu, M.Y., and Tuzel, O. (2016). Coupled generative adversarial networks. Advances in Neural Information Processing Systems, NIPS.
35. Bousmalis, K., Silberman, N., Dohan, D., Erhan, D., and Krishnan, D. (2017, January 21–26). Unsupervised pixel–level domain adaptation with generative adversarial networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.18 ↗
36. Liu, M.Y., Breuel, T., and Kautz, J. (2017). Unsupervised image–to–image translation networks. Advances in Neural Information Processing Systems, NIPS.10.1007/978-3-319-70139-4 ↗
37. Sankaranarayanan, S., Balaji, Y., Castillo, C.D., and Chellappa, R. (2017). Generate to adapt: Aligning domains using generative adversarial networks. arXiv.
38. Murez, Z., Kolouri, S., Kriegman, D.J., Ramamoorthi, R., and Kim, K. (2017, January 21–26). Image to Image Translation for Domain Adaptation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2018.00473 ↗
39. Mao, X., Li, Q., Xie, H., Lau, R.Y., Wang, Z., and Smolley, S.P. (2017, January 22–29). Least squares generative adversarial networks. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.304 ↗
40. Arjovsky, M., Chintala, S., and Bottou, L. (2017, January 11–15). Wasserstein generative adversarial networks. Proceedings of the International Conference on Machine Learning, Sydney, Australia.
41. Karras, T., Aila, T., Laine, S., and Lehtinen, J. (May, January 30). Progressive Growing of GANs for Improved Quality, Stability, and Variation. Proceedings of the International Conference on Learning Representations, Vancouver, BC, Canada.
42. Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., and Chen, X. (2016). Improved techniques for training GANs. Advances in Neural Information Processing Systems, NIPS.
43. Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., and Abbeel, P. (2016). Infogan: Interpretable representation learning by information maximizing generative adversarial nets. Advances in Neural Information Processing Systems, NIPS.
44. Reed, S.E., Akata, Z., Mohan, S., Tenka, S., Schiele, B., and Lee, H. (2016). Learning what and where to draw. Advances in Neural Information Processing Systems, NIPS.
45. Mirza, M., and Osindero, S. (2014). Conditional generative adversarial nets. arXiv.
46. Neal, R.M. (2012). Bayesian Learning for Neural Networks, Springer Science & Business Media.
47. Gal, Y., and Ghahramani, Z. (2016, January 19–24). Dropout as a Bayesian approximation: Representing model uncertainty in deep learning. Proceedings of the International Conference on Machine Learning, New York City, NY, USA.
48. Louizos, C., and Welling, M. (2017, January 11–15). Multiplicative Normalizing Flows for Variational Bayesian Neural Networks. Proceedings of the International Conference on Machine Learning, Sydney, Australia.
49. Atanov, A., Ashukha, A., Molchanov, D., Neklyudov, K., and Vetrov, D. (May, January 30). Uncertainty Estimation via Stochastic Batch Normalization. Proceedings of the International Conference on Learning Representations, Vancouver, BC, Canada.
50. Lakshminarayanan, B., Pritzel, A., and Blundell, C. (2017). Simple and scalable predictive uncertainty estimation using deep ensembles. Advances in Neural Information Processing Systems, NIPS.
51. Kendall, A., and Gal, Y. (2017). What uncertainties do we need in bayesian deep learning for computer vision?. Advances in Neural Information Processing Systems, NIPS.
52. DeVries, T., and Taylor, G.W. (2018). Learning Confidence for Out–of–Distribution Detection in Neural Networks. arXiv.
53. DeVries, T., and Taylor, G.W. (2018). Leveraging Uncertainty Estimates for Predicting Segmentation Quality. arXiv.
54. Guo, C., Pleiss, G., Sun, Y., and Weinberger, K.Q. (2017). On calibration of modern neural networks. arXiv.
55. Mallidi, S.H., Ogawa, T., and Hermansky, H. (2015, January 13–17). Uncertainty estimation of DNN classifiers. Proceedings of the 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), Scottsdale, AZ, USA.10.1109/ASRU.2015.7404806 ↗
56. Goodfellow, I.J., Shlens, J., and Szegedy, C. (2014). Explaining and Harnessing Adversarial Examples. arXiv.
57. French, G., Mackiewicz, M., and Fisher, M. (2017). Self–ensembling for visual domain adaptation. arXiv.