nips nips2013 nips2013-276 nips2013-276-reference knowledge-graph by maker-knowledge-mining

276 nips-2013-Reshaping Visual Datasets for Domain Adaptation


Source: pdf

Author: Boqing Gong, Kristen Grauman, Fei Sha

Abstract: In visual recognition problems, the common data distribution mismatches between training and testing make domain adaptation essential. However, image data is difficult to manually divide into the discrete domains required by adaptation algorithms, and the standard practice of equating datasets with domains is a weak proxy for all the real conditions that alter the statistics in complex ways (lighting, pose, background, resolution, etc.) We propose an approach to automatically discover latent domains in image or video datasets. Our formulation imposes two key properties on domains: maximum distinctiveness and maximum learnability. By maximum distinctiveness, we require the underlying distributions of the identified domains to be different from each other to the maximum extent; by maximum learnability, we ensure that a strong discriminative model can be learned from the domain. We devise a nonparametric formulation and efficient optimization procedure that can successfully discover domains among both training and test data. We extensively evaluate our approach on object recognition and human activity recognition tasks. 1


reference text

[1] L. Duan, D. Xu, I.W. Tsang, and J. Luo. Visual event recognition in videos by learning from web data. In CVPR, 2010.

[2] K. Saenko, B. Kulis, M. Fritz, and T. Darrell. Adapting visual category models to new domains. In ECCV, 2010.

[3] R. Gopalan, R. Li, and R. Chellappa. Domain adaptation for object recognition: An unsupervised approach. In ICCV, 2011.

[4] B. Gong, Y. Shi, F. Sha, and K. Grauman. Geodesic flow kernel for unsupervised domain adaptation. In CVPR, 2012.

[5] H. Daum´ III. Frustratingly easy domain adaptation. In ACL, 2007. e

[6] J. Blitzer, R. McDonald, and F. Pereira. Domain adaptation with structural correspondence learning. In EMNLP, 2006.

[7] J. Huang, A.J. Smola, A. Gretton, K.M. Borgwardt, and B. Scholkopf. Correcting sample selection bias by unlabeled data. In NIPS, 2007.

[8] S.J. Pan, I.W. Tsang, J.T. Kwok, and Q. Yang. Domain adaptation via transfer component analysis. IEEE Trans. NN, (99):1–12, 2009.

[9] J. Quionero-Candela, M. Sugiyama, A. Schwaighofer, and N.D. Lawrence. Dataset shift in machine learning. The MIT Press, 2009.

[10] Y. Mansour, M. Mohri, and A. Rostamizadeh. Domain adaptation with multiple sources. In NIPS, 2009.

[11] 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.

[12] M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman. The pascal visual object classes (voc) challenge. International Journal of Computer Vision, 88(2):303–338, 2010.

[13] B. C. Russell, A. Torralba, K. P. Murphy, and W. T. Freeman. LabelMe: a database and web-based tool for image annotation. IJCV, 77:157–173, 2008.

[14] G. Griffin, A. Holub, and P. Perona. Caltech-256 object category dataset. Technical report, California Institute of Technology, 2007.

[15] D. Weinland, E. Boyer, and R. Ronfard. Action recognition from arbitrary views using 3d exemplars. In ICCV, 2007.

[16] A. Torralba and A.A. Efros. Unbiased look at dataset bias. In CVPR, 2011.

[17] B. Gong, F. Sha, and K. Grauman. Overcoming dataset bias: An unsupervised domain adaptation approach. In NIPS Workshop on Large Scale Visual Recognition and Retrieval, 2012.

[18] L. Cao, Z. Liu, and T. S Huang. Cross-dataset action detection. In CVPR, 2010.

[19] T. Tommasi, N. Quadrianto, B. Caputo, and C. Lampert. Beyond dataset bias: multi-task unaligned shared knowledge transfer. In ACCV, 2012.

[20] J. Hoffman, B. Kulis, T. Darrell, and K. Saenko. Discovering latent domains for multisource domain adaptation. In ECCV. 2012.

[21] A. Gretton, K. Borgwardt, M. Rasch, B. Schoelkopf, and A. Smola. A kernel method for the two-sampleproblem. In NIPS. 2007.

[22] H. Shimodaira. Improving predictive inference under covariate shift by weighting the log-likelihood function. Journal of Statistical Planning and Inference, 90(2):227–244, 2000.

[23] S. Ben-David, J. Blitzer, K. Crammer, and F. Pereira. Analysis of representations for domain adaptation. In NIPS, 2007.

[24] R. Li and T. Zickler. Discriminative virtual views for cross-view action recognition. In CVPR, 2012.

[25] K. Tang, V. Ramanathan, L. Fei-Fei, and D. Koller. Shifting weights: Adapting object detectors from image to video. In NIPS, 2012.

[26] B. Gong, K. Grauman, and F. Sha. Connecting the dots with landmarks: Discriminatively learning domain-invariant features for unsupervised domain adaptation. In ICML, 2013.

[27] S. Jegelka, A. Gretton, B. Sch¨ lkopf, B. K Sriperumbudur, and U. Von Luxburg. Generalized clustering o via kernel embeddings. In Advances in Artificial Intelligence, 2009.

[28] Q. Sun, R. Chattopadhyay, S. Panchanathan, and J. Ye. A two-stage weighting framework for multi-source domain adaptation. In NIPS, 2011.

[29] L. Duan, I. W Tsang, D. Xu, and T. Chua. Domain adaptation from multiple sources via auxiliary classifiers. In ICML, 2009.

[30] H. Bay, T. Tuytelaars, and L. Van Gool. SURF: Speeded up robust features. In ECCV, 2006.

[31] D. Tran and A. Sorokin. Human activity recognition with metric learning. In ECCV. 2008.

[32] A. Bergamo and L. Torresani. Exploiting weakly-labeled web images to improve object classification: a domain adaptation approach. In NIPS, 2010.

[33] A. Farhadi and M. Tabrizi. Learning to recognize activities from the wrong view point. In ECCV, 2008.

[34] C.-H. Huang, Y.-R. Yeh, and Y.-C. Wang. Recognizing actions across cameras by exploring the correlated subspace. In ECCV, 2012.

[35] J. Liu, M. Shah, B. Kuipers, and S. Savarese. Cross-view action recognition via view knowledge transfer. In CVPR, 2011. 9