Abstract
The presence of bias in existing object recognition datasets is now well-known in the computer vision community. While it remains in question whether creating an unbiased dataset is possible given limited resources, in this work we propose a discriminative framework that directly exploits dataset bias during training. In particular, our model learns two sets of weights: (1) bias vectors associated with each individual dataset, and (2) visual world weights that are common to all datasets, which are learned by undoing the associated bias from each dataset. The visual world weights are expected to be our best possible approximation to the object model trained on an unbiased dataset, and thus tend to have good generalization ability. We demonstrate the effectiveness of our model by applying the learned weights to a novel, unseen dataset, and report superior results for both classification and detection tasks compared to a classical SVM that does not account for the presence of bias. Overall, we find that it is beneficial to explicitly account for bias when combining multiple datasets.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Torralba, A., Fergus, R., Freeman, W.T.: 80 million tiny images: A large data set for nonparametric object and scene recognition. PAMI 30(11), 1958–1970 (2008)
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: ImageNet: A Large-Scale Hierarchical Image Database. In: CVPR (2009)
Everingham, M., Gool, L.V., Williams, C.K.I., Winn, J., Zisserman, A.: The pascal visual object classes (voc) challenge. IJCV 88, 303–338 (2010)
Torralba, A., Efros, A.A.: Unbiased look at dataset bias. In: CVPR, pp. 1521–1528 (2011)
Ponce, J., Berg, T.L., Everingham, M., Forsyth, D., Hebert, M., Lazebnik, S., Marszalek, M., Schmid, C., Russell, B.C., Torralba, A., Williams, C.K.I., Zhang, J., Zisserman, A.: Dataset Issues in Object Recognition. In: Ponce, J., Hebert, M., Schmid, C., Zisserman, A. (eds.) Toward Category-Level Object Recognition. LNCS, vol. 4170, pp. 29–48. Springer, Heidelberg (2006)
Quinonero-Candela, J., Sugiyama, M., Schwaighofer, A., Lawrence, N.: Dataset shift in machine learning. MIT Press (2009)
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)
Kulis, B., Saenko, K., Darrell, T.: What you saw is not what you get: Domain adaptation using asymmetric kernel transforms. In: CVPR (2011)
Gopalan, R., Li, R., Chellappa, R.: Domain adaptation for object recognition: An unsupervised approach. In: ICCV (2011)
Jain, V., Learned-Miller, E.: Online domain adaptation of a pre-trained cascade of classifiers. In: CVPR (2011)
Evgeniou, T., Pontil, M.: Regularized multi–task learning. In: 10th ACM SIGKDD International Conf. Knowledge Discovery and Data Mining, pp. 109–117 (2004)
Ben-David, S., Schuller, R.: Exploiting Task Relatedness for Multiple Task Learning. In: Schölkopf, B., Warmuth, M.K. (eds.) COLT/Kernel 2003. LNCS (LNAI), vol. 2777, pp. 567–580. Springer, Heidelberg (2003)
Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering 22 (2010)
Bergamo, A., Torresani, L., Fitzgibbon, A.: Picodes: Learning a compact code for novel-category recognition. In: NIPS (2011)
Perronnin, F., Sánchez, J., Liu, Y.: Large-scale image categorization with explicit data embedding. In: CVPR, pp. 2297–2304. IEEE (2010)
Perronnin, F., Sánchez, J., Mensink, T.: Improving the Fisher Kernel for Large-Scale Image Classification. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 143–156. Springer, Heidelberg (2010)
Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. PAMI 32(9), 1627–1645 (2010)
Russell, B., Torralba, A., Murphy, K.P., Freeman, W.T.: Labelme: a database and web-based tool for image annotation. In: IJCV (2007)
Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories. In: CVPR Workshop of Generative Model Based Vision (2004)
Choi, M.J., Lim, J.J., Torralba, A., Willsky, A.S.: Exploiting hierarchical context on a large database of object categories. In: CVPR, pp. 129–136 (2010)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV 60, 91–110 (2004)
Wang, J., Yang, J., Yu, K., Lv, F., Huang, T., Gong, Y.: Locality-constrained linear coding for image classification. In: CVPR (2010)
Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: CVPR (2006)
Fan, R.E., Chang, K.W., Hsieh, C.J., Wang, X.R., Lin, C.J.: Liblinear: A library for large linear classification. JMLR 9, 1871–1874 (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Khosla, A., Zhou, T., Malisiewicz, T., Efros, A.A., Torralba, A. (2012). Undoing the Damage of Dataset Bias. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds) Computer Vision – ECCV 2012. ECCV 2012. Lecture Notes in Computer Science, vol 7572. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33718-5_12
Download citation
DOI: https://doi.org/10.1007/978-3-642-33718-5_12
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33717-8
Online ISBN: 978-3-642-33718-5
eBook Packages: Computer ScienceComputer Science (R0)