Advertisement

A Deeper Look at Dataset Bias

  • Tatiana Tommasi
  • Novi Patricia
  • Barbara Caputo
  • Tinne Tuytelaars
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9358)

Abstract

The presence of a bias in each image data collection has recently attracted a lot of attention in the computer vision community showing the limits in generalization of any learning method trained on a specific dataset. At the same time, with the rapid development of deep learning architectures, the activation values of Convolutional Neural Networks (CNN) are emerging as reliable and robust image descriptors. In this paper we propose to verify the potential of the DeCAF features when facing the dataset bias problem. We conduct a series of analyses looking at how existing datasets differ among each other and verifying the performance of existing debiasing methods under different representations. We learn important lessons on which part of the dataset bias problem can be considered solved and which open questions still need to be tackled.

Supplementary material

371393_1_En_42_MOESM1_ESM.zip (1.1 mb)
Supplementary material 1 (zip 1136 KB)

References

  1. 1.
    Agrawal, P., Girshick, R., Malik, J.: Analyzing the performance of multilayer neural networks for object recognition. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part VII. LNCS, vol. 8695, pp. 329–344. Springer, Heidelberg (2014) Google Scholar
  2. 2.
    Ben-David, S., Blitzer, J., Crammer, K., Pereira, F.: Analysis of representations for domain adaptation. In: NIPS (2007)Google Scholar
  3. 3.
    Chatfield, K., Simonyan, K., Vedaldi, A., Zisserman, A.: Return of the devil in the details: delving deep into convolutional nets. In: BMVC (2014)Google Scholar
  4. 4.
    Chatfield, K., Simonyan, K., Zisserman, A.: Efficient on-the-fly category retrieval using ConvNets and GPUs. In: Cremers, D., Reid, I., Saito, H., Yang, M.-H. (eds.) ACCV 2014. LNCS, vol. 9003, pp. 129–145. Springer, Heidelberg (2015) Google Scholar
  5. 5.
    Deng, J., Dong, W., Socher, R., Li, L., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: CVPR (2009)Google Scholar
  6. 6.
    Donahue, J., Jia, Y., Vinyals, O., Hoffman, J., Zhang, N., Tzeng, E., Darrell, T.: Decaf: a deep convolutional activation feature for generic visual recognition. In: ICML (2014). https://github.com/UCB-ICSI-Vision-Group/decaf-release/
  7. 7.
    Duan, L., Tsang, I.W., Xu, D., Chua, T.S.: Domain adaptation from multiple sources via auxiliary classifiers. In: ICML (2009)Google Scholar
  8. 8.
    Everingham, M., Gool, L.V., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. IJCV 88(2), 303–338 (2010)CrossRefGoogle Scholar
  9. 9.
    Farhadi, A., Endres, I., Hoiem, D., Forsyth, D.: Describing objects by their attributes. In: CVPR (2009)Google Scholar
  10. 10.
    Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: an incremental bayesian approach tested on 101 object categories. Comput. Vis. Image Underst. 106(1), 59–70 (2007)CrossRefGoogle Scholar
  11. 11.
    Fernando, B., Habrard, A., Sebban, M., Tuytelaars, T.: Unsupervised visual domain adaptation using subspace alignment. In: ICCV (2013)Google Scholar
  12. 12.
    Gong, B., Grauman, K., Sha, F.: Connecting the dots with landmarks: discriminatively learning domain-invariant features for unsupervised domain adaptation. In: ICML (2013)Google Scholar
  13. 13.
    Gong, B., Shi, Y., Sha, F., Grauman, K.: Geodesic flow kernel for unsupervised domain adaptation. In: CVPR (2012)Google Scholar
  14. 14.
    Gong, Y., Wang, L., Guo, R., Lazebnik, S.: Multi-scale orderless pooling of deep convolutional activation features. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part VII. LNCS, vol. 8695, pp. 392–407. Springer, Heidelberg (2014) Google Scholar
  15. 15.
    Griffin, G., Holub, A., Perona, P.: Caltech 256 object category dataset. Technical report UCB/CSD-04-1366, California Institue of Technology (2007)Google Scholar
  16. 16.
    Hoffman, J., Guadarrama, S., Tzeng, E., Hu, R., Donahue, J., Girshick, R., Darrell, T., Saenko, K.: LSDA: Large scale detection through adaptation. In: NIPS (2014)Google Scholar
  17. 17.
    Hoffman, J., Kulis, B., Darrell, T., Saenko, K.: Discovering latent domains for multisource domain adaptation. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part II. LNCS, vol. 7573, pp. 702–715. Springer, Heidelberg (2012) CrossRefGoogle Scholar
  18. 18.
    Hoffman, J., Tzeng, E., Donahue, J., Jia, Y., Saenko, K., Darrell, T.: One-shot adaptation of supervised deep convolutional models (2014)Google Scholar
  19. 19.
    Khosla, A., Zhou, T., Malisiewicz, T., Efros, A.A., Torralba, A.: Undoing the damage of dataset bias. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part I. LNCS, vol. 7572, pp. 158–171. Springer, Heidelberg (2012) CrossRefGoogle Scholar
  20. 20.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS (2012)Google Scholar
  21. 21.
    Lai, K., Bo, L., Ren, X., Fox, D.: A large-scale hierarchical multi-view rgb-d object dataset. In: ICRA (2011)Google Scholar
  22. 22.
    Lampert, C.H., Nickisch, H., Harmeling, S.: Learning to detect unseen object classes by between class attribute transfer. In: CVPR (2009)Google Scholar
  23. 23.
    Leibe, B., Schiele, B.: Analyzing appearance and contour based methods for object categorization. In: CVPR (2003)Google Scholar
  24. 24.
    Lowe, D.G.: Object recognition from local scale-invariant features. In: ICCV (1999)Google Scholar
  25. 25.
    Microsoft.: Microsoft Research Cambridge Object Recognition Image Database (2005). http://research.microsoft.com/en-us/downloads/b94de342-60dc-45d0-830b-9f6eff91b301/default.aspx
  26. 26.
    Oquab, M., Bottou, L., Laptev, I., Sivic, J.: Learning and transferring mid-level image representations using convolutional neural networks. In: CVPR (2014)Google Scholar
  27. 27.
    Razavian, A.S., Azizpour, H., Sullivan, J., Carlsson, S.: CNN Features off-the-shelf: an Astounding Baseline for Recognition (2014). arXiv:1403.6382
  28. 28.
    Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., Berg, A.C., Fei-Fei, L.: ImageNet large scale visual recognition challenge (2014). arXiv:1409.0575
  29. 29.
    Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., Berg, A.C., Fei-Fei, L.: ImageNet Large Scale Visual Recognition Challenge. Int. J. Comput. Vis. (IJCV), 1–42 (2015). doi: 10.1007/s11263-015-0816-y
  30. 30.
    Chopra, S., Balakrishnan, S., Gopalan, R.: DLID: deep learning for domain adaptation by interpolating between domains. In: ICML Workshop on Challenges in Representation Learning (2013)Google Scholar
  31. 31.
    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, Part IV. LNCS, vol. 6314, pp. 213–226. Springer, Heidelberg (2010) CrossRefGoogle Scholar
  32. 32.
    Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., LeCun, Y.: Overfeat: integrated recognition, localization and detection using convolutional networks. In: ICLR (2014)Google Scholar
  33. 33.
    Tommasi, T., Tuytelaars, T.: A testbed for cross-dataset analysis. In: Agapito, L., Bronstein, M.M., Rother, C. (eds.) ECCV 2014 Workshops. LNCS, vol. 8927, pp. 18–31. Springer, Heidelberg (2015) Google Scholar
  34. 34.
    Torralba, A., Efros, A.A.: Unbiased look at dataset bias. In: CVPR (2011)Google Scholar
  35. 35.
    Torresani, L., Szummer, M., Fitzgibbon, A.: Efficient object category recognition using classemes. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part I. LNCS, vol. 6311, pp. 776–789. Springer, Heidelberg (2010) CrossRefGoogle Scholar
  36. 36.
    Xiao, J., Hays, J., Ehinger, K.A., Oliva, A., Torralba, A.: Sun database: large-scale scene recognition from abbey to zoo. In: CVPR (2010)Google Scholar
  37. 37.
    Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part I. LNCS, vol. 8689, pp. 818–833. Springer, Heidelberg (2014) Google Scholar
  38. 38.
    Zhang, N., Donahue, J., Girshick, R., Darrell, T.: Part-based R-CNNs for fine-grained category detection. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part I. LNCS, vol. 8689, pp. 834–849. Springer, Heidelberg (2014) Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Open Access This chapter is distributed under the terms of the Creative Commons Attribution Noncommercial License, which permits any noncommercial use, distribution, and reproduction in any medium, provided the original author(s) and source are credited.

Authors and Affiliations

  • Tatiana Tommasi
    • 1
  • Novi Patricia
    • 2
    • 3
  • Barbara Caputo
    • 4
  • Tinne Tuytelaars
    • 5
  1. 1.Department of Computer ScienceUniversity of North CarolinaChapel HillUSA
  2. 2.Idiap Research InstituteMartignySwitzerland
  3. 3.EPFLLausanneSwitzerland
  4. 4.La Sapienza University of RomeRomeItaly
  5. 5.KU Leuven, ESAT-PSI, iMindsLeuvenBelgium

Personalised recommendations