Advertisement

On the Effectiveness of Image Rotation for Open Set Domain Adaptation

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12361)

Abstract

Open Set Domain Adaptation (OSDA) bridges the domain gap between a labeled source domain and an unlabeled target domain, while also rejecting target classes that are not present in the source. To avoid negative transfer, OSDA can be tackled by first separating the known/unknown target samples and then aligning known target samples with the source data. We propose a novel method to addresses both these problems using the self-supervised task of rotation recognition. Moreover, we assess the performance with a new open set metric that properly balances the contribution of recognizing the known classes and rejecting the unknown samples. Comparative experiments with existing OSDA methods on the standard Office-31 and Office-Home benchmarks show that: (i) our method outperforms its competitors, (ii) reproducibility for this field is a crucial issue to tackle, (iii) our metric provides a reliable tool to allow fair open set evaluation.

Keywords

Open Set Domain Adaptation Self-supervised learning 

Notes

Acknowledgements

This work was partially founded by the ERC grant 637076 RoboExNovo (SB), by the H2020 ACROSSING project grant 676157 (MRL) and took advantage of the NVIDIA GPU Academic Hardware Grant (TT).

Supplementary material

504471_1_En_25_MOESM1_ESM.pdf (747 kb)
Supplementary material 1 (pdf 747 KB)

References

  1. 1.
    Bendale, A., Boult, T.E.: Towards open set deep networks. In: CVPR (2016)Google Scholar
  2. 2.
    Bergman, L., Hoshen, Y.: Classification-based anomaly detection for general data. In: ICLR (2020)Google Scholar
  3. 3.
    Bousmalis, K., Trigeorgis, G., Silberman, N., Krishnan, D., Erhan, D.: Domain separation networks. In: NeurIPS (2016)Google Scholar
  4. 4.
    Candès, E.J., Li, X., Ma, Y., Wright, J.: Robust principal component analysis? J. ACM 58(3), 1–37 (2011)MathSciNetzbMATHCrossRefGoogle Scholar
  5. 5.
    Carlucci, F.M., D’Innocente, A., Bucci, S., Caputo, B., Tommasi, T.: Domain generalization by solving jigsaw puzzles. In: CVPR (2019)Google Scholar
  6. 6.
    Reproducibility challenge. https://reproducibility-challenge.github.io/neurips2019/. Accessed 4 Mar 2020
  7. 7.
    The machine learning reproducibility checklist. https://www.cs.mcgill.ca/~jpineau/ReproducibilityChecklist.pdf. Accessed 4 Mar 2020
  8. 8.
    Csurka, G.: Domain Adaptation in Computer Vision Applications, 1st edn. Springer Publishing Company, Incorporated (2017)Google Scholar
  9. 9.
    Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: CVPR (2009)Google Scholar
  10. 10.
    Dodge, J., Gururangan, S., Card, D., Schwartz, R., Smith, N.A.: Show your work: improved reporting of experimental results. In: EMNLP (2019)Google Scholar
  11. 11.
    Doersch, C., Gupta, A., Efros, A.A.: Unsupervised visual representation learning by context prediction. In: ICCV (2015)Google Scholar
  12. 12.
    Eskin, E., Arnold, A., Prerau, M., Portnoy, L., Stolfo, S.: A geometric framework for unsupervised anomaly detection. In: Barbará, D., Jajodia, S. (eds.) Applications of Data Mining in Computer Security. Advances in Information Security, vol 6, pp. 77–101. Springer, Boston (2002)Google Scholar
  13. 13.
    Feng, Q., Kang, G., Fan, H., Yang, Y.: Attract or distract: exploit the margin of open set. In: ICCV (2019)Google Scholar
  14. 14.
    Ganin, Y., et al.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17(1), 1–35 (2016)MathSciNetzbMATHGoogle Scholar
  15. 15.
    Ghifary, M., Kleijn, W.B., Zhang, M., Balduzzi, D., Li, W.: Deep reconstruction-classification networks for unsupervised domain adaptation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 597–613. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46493-0_36CrossRefGoogle Scholar
  16. 16.
    Gidaris, S., Singh, P., Komodakis, N.: Unsupervised representation learning by predicting image rotations. arXiv preprint arXiv:1803.07728 (2018)
  17. 17.
    Golan, I., El-Yaniv, R.: Deep anomaly detection using geometric transformations. In: NeurIPS (2018)Google Scholar
  18. 18.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)Google Scholar
  19. 19.
    Henderson, P., Islam, R., Bachman, P., Pineau, J., Precup, D., Meger, D.: Deep reinforcement learning that matters. In: AAAI (2018)Google Scholar
  20. 20.
    Hendrycks, D., Gimpel, K.: A baseline for detecting misclassified and out-of-distribution examples in neural networks. In: ICLR (2017)Google Scholar
  21. 21.
    Kim, J., Scott, C.D.: Robust kernel density estimation. J. Mach. Learn. Res. 13(1), 2529–2565 (2012)MathSciNetzbMATHGoogle Scholar
  22. 22.
    Larsson, G., Maire, M., Shakhnarovich, G.: Colorization as a proxy task for visual understanding. In: CVPR (2017)Google Scholar
  23. 23.
    Liang, S., Li, Y., Srikant, R.: Enhancing the reliability of out-of-distribution image detection in neural networks. In: ICLR (2018)Google Scholar
  24. 24.
    Liu, H., Cao, Z., Long, M., Wang, J., Yang, Q.: Separate to adapt: open set domain adaptation via progressive separation. In: CVPR (2019)Google Scholar
  25. 25.
    Loghmani, M.R., Vincze, M., Tommasi, T.: Positive-unlabeled learning for open set domain adaptation. Pattern Recogn. Lett. 136, 198–204 (2020)CrossRefGoogle Scholar
  26. 26.
    Long, M., Cao, Y., Wang, J., Jordan, M.I.: Learning transferable features with deep adaptation networks. In: ICML (2015)Google Scholar
  27. 27.
    Lucic, M., Kurach, K., Michalski, M., Gelly, S., Bousquet, O.: Are gans created equal? a large-scale study. In: NeurIPS (2018)Google Scholar
  28. 28.
    Noroozi, M., Favaro, P.: Unsupervised learning of visual representations by solving jigsaw puzzles. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 69–84. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46466-4_5CrossRefGoogle Scholar
  29. 29.
    Panareda Busto, P., Gall, J.: Open set domain adaptation. In: ICCV (2017)Google Scholar
  30. 30.
    Pathak, D., Krähenbühl, P., Donahue, J., Darrell, T., Efros, A.: Context encoders: feature learning by inpainting. In: CVPR (2016)Google Scholar
  31. 31.
    Ruff, L., et al.: Deep one-class classification. In: ICML (2018)Google Scholar
  32. 32.
    Russo, P., Carlucci, F.M., Tommasi, T., Caputo, B.: From source to target and back: symmetric bi-directional adaptive gan. In: CVPR (2018)Google Scholar
  33. 33.
    Saenko, K., Kulis, B., Fritz, M., Darrell, T.: Adapting visual category models to new domains. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 213–226. Springer, Heidelberg (2010).  https://doi.org/10.1007/978-3-642-15561-1_16CrossRefGoogle Scholar
  34. 34.
    Saito, K., Yamamoto, S., Ushiku, Y., Harada, T.: Open set domain adaptation by backpropagation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 156–171. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01228-1_10CrossRefGoogle Scholar
  35. 35.
    Saito, K., Yamamoto, S., Ushiku, Y., Harada, T.: Open set domain adaptation by backpropagation. arXiv preprint arXiv:1804.10427 (2018)
  36. 36.
    Schlegl, T., Seeböck, P., Waldstein, S.M., Schmidt-Erfurth, U., Langs, G.: Unsupervised anomaly detection with generative adversarial networks to guide marker discovery. In: IPMI (2017)Google Scholar
  37. 37.
    Schölkopf, B., Williamson, R., Smola, A., Shawe-Taylor, J., Platt, J.: Support vector method for novelty detection. In: NeurIPS (1999)Google Scholar
  38. 38.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
  39. 39.
    Sun, B., Feng, J., Saenko, K.: Return of frustratingly easy domain adaptation. In: AAAI (2016)Google Scholar
  40. 40.
    Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: CVPR (2017)Google Scholar
  41. 41.
    Venkateswara, H., Eusebio, J., Chakraborty, S., Panchanathan, S.: Deep hashing network for unsupervised domain adaptation. In: CVPR (2017)Google Scholar
  42. 42.
    Wen, Y., Zhang, K., Li, Z., Qiao, Yu.: A discriminative feature learning approach for deep face recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 499–515. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46478-7_31CrossRefGoogle Scholar
  43. 43.
    Xia, Y., Cao, X., Wen, F., Hua, G., Sun, J.: Learning discriminative reconstructions for unsupervised outlier removal. In: ICCV (2015)Google Scholar
  44. 44.
    Xu, J., Xiao, L., López, A.M.: Self-supervised domain adaptation for computer vision tasks. IEEE Access 7, 156694–156706 (2019)CrossRefGoogle Scholar
  45. 45.
    Xu, R., Li, G., Yang, J., Lin, L.: Larger norm more transferable: an adaptive feature norm approach for unsupervised domain adaptation. In: ICCV (2019)Google Scholar
  46. 46.
    You, K., Long, M., Cao, Z., Wang, J., Jordan, M.I.: Universal domain adaptation. In: CVPR (2019)Google Scholar
  47. 47.
    Zhai, S., Cheng, Y., Lu, W., Zhang, Z.: Deep structured energy based models for anomaly detection. In: ICML (2016)Google Scholar
  48. 48.
    Zhang, R., Isola, P., Efros, A.A.: Colorful image colorization. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 649–666. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46487-9_40CrossRefGoogle Scholar
  49. 49.
    Zhou, C., Paffenroth, R.C.: Anomaly detection with robust deep autoencoders. In: ACM SIGKDD (2017)Google Scholar
  50. 50.
    Zimek, A., Schubert, E., Kriegel, H.P.: A survey on unsupervised outlier detection in high-dimensional numerical data. Stat. Anal. Data Mining ASA Data Sci. J. 5, 363–387 (2012)MathSciNetzbMATHCrossRefGoogle Scholar
  51. 51.
    Zong, B., et al.: Deep autoencoding gaussian mixture model for unsupervised anomaly detection. In: ICLR (2018)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Italian Institute of TechnologyGenovaItaly
  2. 2.Politecnico di TorinoTurinItaly
  3. 3.Vision for Robotics laboratory, ACINTU WienViennaAustria

Personalised recommendations