iccv iccv2013 iccv2013-181 iccv2013-181-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Tatiana Tommasi, Barbara Caputo
Abstract: Over the last years, several authors have signaled that state of the art categorization methods fail to perform well when trained and tested on data from different databases. The general consensus in the literature is that this issue, known as domain adaptation and/or dataset bias, is due to a distribution mismatch between data collections. Methods addressing it go from max-margin classifiers to learning how to modify the features and obtain a more robust representation. The large majority of these works use BOW feature descriptors, and learning methods based on imageto-image distance functions. Following the seminal work of [6], in this paper we challenge these two assumptions. We experimentally show that using the NBNN classifier over existing domain adaptation databases achieves always very strong performances. We build on this result, and present an NBNN-based domain adaptation algorithm that learns iteratively a class metric while inducing, for each sample, a large margin separation among classes. To the best of our knowledge, this is the first work casting the domain adaptation problem within the NBNN framework. Experiments show that our method achieves the state of the art, both in the unsupervised and semi-supervised settings.
[1] H. Bay, A. Ess, T. Tuytelaars, and L. V. Gool. SURF: Speeded up robust features. CVIU, 110:346–359, 2008.
[2] R. Behmo, P. Marcombes, A. Dalalyan, and V. Prinet. Towards optimal Naive Bayes Nearest Neighbor. In ECCV, 2010.
[3] S. Ben-David, J. Blitzer, K. Crammer, and F. Pereira. Analysis of representations for domain adaptation. In NIPS, 2007.
[4] A. Bergamo and L. Torresani. Exploiting weakly-labeled web images to improve object classification: a domain adaptation approach. In NIPS, 2010.
[5] J. Blitzer, R. McDonald, and F. Pereira. Domain adaptation with structural correspondence learning. In EMNLP, 2006.
[6] O. Boiman, E. Shechtman, and M. Irani. In defense of nearest-neighbor based image classification. In CVPR, 2008. 990044
[7] L. Bruzzone and M. Marconcini. Domain adaptation prob-
[8]
[9]
[10]
[11]
[12]
[13]
[14]
[15]
[16]
[17]
[18]
[19] lems: A DASVM classification technique and a circular validation strategy. IEEE PAMI, 32(5):770–787, 2010. H. Daum e´ III. Frustratingly easy domain adaptation. In ACL, 2007. J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei. ImageNet: A Large-Scale Hierarchical Image Database. In CVPR, 2009. L. Duan, I. W.-H. Tsang, D. Xu, and S. J. Maybank. Domain transfer svm for video concept detection. In CVPR, 2009. M. Everingham, L. V. Gool, C. K. Williams, J. Winn, and A. Zisserman. The Pascal Visual Object Classes (VOC) Challenge. IJCV, 88(2), 2010. B. Gong, Y. Shi, F. Sha, and K. Grauman. Geodesic flow kernel for unsupervised domain adaptation. In CVPR, 2012. R. Gopalan, R. Li, and R. Chellappa. Domain adaptation for object recognition: An unsupervised approach. In ICCV, 2011. G. Griffin, A. Holub, and P. Perona. Caltech 256 object category dataset. Technical Report UCB/CSD-04-1366, California Institue of Technology, 2007. A. Khosla, T. Zhou, T. Malisiewicz, A. Efros, and A. Torralba. Undoing the damage of dataset bias. In ECCV, 2012. S. Lazebnik, C. Schmid, and J. Ponce. Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In CVPR, 2006. J. J. Lim, R. Salakhutdinov, and A. Torralba. Transfer learning by borrowing examples for multiclass object detection. In NIPS, 2011. S. Lyu. Mercer kernels for object recognition with local features. In CVPR, 2005. J. Ni, Q. Qiu, and R. Chellappa. Subspace interpolation via
[20]
[21]
[22]
[23]
[24]
[25]
[26]
[27]
[28]
[29] dictionary learning for unsupervised domain adaptation. In CVPR, 2013. Q. Qiu, V. M. Patel, P. Turaga, and R. Chellappa. Domain adaptive dictionary learning. In ECCV, 2012. J. Quionero-Candela, M. Sugiyama, A. Schwaighofer, and N. D. Lawrence. Dataset Shift in Machine Learning. The MIT Press, 2009. K. Saenko, B. Kulis, M. Fritz, and T. Darrell. Adapting visual category models to new domains. In ECCV, 2010. J. Sivic and A. Zisserman. Video google: A text retrieval approach to object matching in videos. In ICCV, 2003. T. Tommasi, N. Quadrianto, B. Caputo, and C. Lampert. Beyond dataset bias: Multi-task unaligned shared knowledge transfer. In ACCV, 2012. A. Torralba and A. A. Efros. Unbiased look at dataset bias. In CVPR, 2011. T. Tuytelaars, M. Fritz, K. Saenko, and T. Darrell. The NBNN kernel. In ICCV, 2011. Z. Wang, Y. Hu, and L.-T. Chia. Image-to-class distance metric learning for image classification. In ECCV, 2010. K. Weinberger and L. Saul. Distance metric learning for large margin nearest neighbor classification. JMLR, 10:207– 244, 2009. J. Yang, R. Yan, and A. G. Hauptmann. Cross-domain video concept detection using adaptive svms. In ACM Multimedia, 2007.