Abstract
In this paper we address the problem of domain adaptation using multiple source domains. We extend the XRCE contribution to Clef’14 Domain Adaptation challenge [6] with the new methods and new datasets. We describe a new class of domain adaptation technique based on stacked marginalized denoising autoencoders (sMDA). It aims at extracting and denoising features common to both source and target domains in the unsupervised mode. Noise marginalization allows to obtain a closed form solution and to considerably reduce the training time. We build a classification system which compares sMDA combined with SVM or with Domain Specific Class Mean classifiers to the state-of-the art in both unsupervised and semi-supervised settings. We report the evaluation results for a number of image and text datasets.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Baktashmotlagh, M., Harandi, M.T., Lovell, B.C., Salzmann, M.: Unsupervised domain adaptation by domain invariant projection. In: ICCV (2013)
Bay, H., Tuytelaars, T., Van Gool, L.: SURF: speeded up robust features. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006, Part I. LNCS, vol. 3951, pp. 404–417. Springer, Heidelberg (2006)
Beijbom, O.: Domain adaptations for computer vision applications (2012). arXiv (1211.4860)
Blitzer, J., Foster, D., Kakade, S.: Domain adaptation with coupled subspaces. In: ICAIS (2011)
Chen, M., Xu, Z., Weinberger, K.Q., Sha, F.: Marginalized denoising autoencoders for domain adaptation (2012). arXiv (1206.4683)
Chidlovskii, B., Csurka, G., Gangwar, S.: Assembling heterogeneous domain adaptation methods for image classification. In: Working Notes for CLEF 2014 (2014)
Clinchant, S.: Concavity in IR models. In: CIKM (2012)
Csurka, G., Chidlovskii, B., Perronnin, F.: Domain adaptation with a domain specific class means classifier. In: Agapito, L., Bronstein, M.M., Rother, C. (eds.) ECCV 2014 Workshops. LNCS, vol. 8927, pp. 32–46. Springer, Heidelberg (2015)
Csurka, G., Dance, C., Fan, L., Willamowski, J., Bray, C.: Visual categorization with bags of keypoints. In: SLCV, ECCV Workshop (2004)
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 (1999)
Fernando, B., Habrard, A., Sebban, M., Tuytelaars, T.: Unsupervised visual domain adaptation using subspace alignment. In: ICCV (2013)
Fernando, B., Habrard, A., Sebban, M., Tuytelaars, T.: Subspace alignment for domain adaptation (2014). arXiv (1409.5241)
Glorot, X., Bordes, A., Bengio, Y.: Domain adaptation for large-scale sentiment classification: a deep learning approach. In: ICML (2011)
Gong, B., Grauman, K., Sha, F.: Reshaping visual datasets for domain adaptation. In: NIPS (2013)
Gopalan, R., Li, R., Chellappa, R.: Domain adaptation for object recognition: an unsupervised approach. In: ICCV (2011)
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)
Jhuo, I.-H., Liu, D., Lee, D.T., Chang, S.-F.: Robust visual domain adaptation with low-rank reconstruction. In: CVPR, pp. 2168–2175 (2012)
Jiang, J.: A literature survey on domain adaptation of statistical classifiers (2008). https://scholar.google.com.sg/citations?user=hVTK2YwAAAAJ
Kulis, B., Saenko, K., Darrell, T.: What you saw is not what you get: domain adaptation using asymmetric kernel transforms. In: CVPR (2011)
Lowe, D.G.: Object recognition from local scale-invariant features. In: ICCV (1999)
Patel, V.M., Gopalan, R., Li, R., Chellappa, R.: Visual domain adaptation: An overview of recent advances. IEEE Transactions on Geoscience and Remote Sensing 52(2) (2007)
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)
Tommasi, T., Caputo, B.: Frustratingly easy NBNN domain adaptation. In: ICCV (2013)
Torralba, A., Efros, A.: Unbiased look at dataset bias. In: CVPR (2011)
Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.-A.: Extracting and composing robust features with denoising autoencoders. In: ICML (2008)
Xu, Z., Chen, M., Weinberger, K.Q., Sha, F.: From sBoW to dCoT marginalized encoders for text representation. In: CIKM (2012)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Chidlovskii, B., Csurka, G., Clinchant, S. (2015). Evaluating Stacked Marginalised Denoising Autoencoders Within Domain Adaptation Methods. In: Mothe, J., et al. Experimental IR Meets Multilinguality, Multimodality, and Interaction. CLEF 2015. Lecture Notes in Computer Science(), vol 9283. Springer, Cham. https://doi.org/10.1007/978-3-319-24027-5_2
Download citation
DOI: https://doi.org/10.1007/978-3-319-24027-5_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-24026-8
Online ISBN: 978-3-319-24027-5
eBook Packages: Computer ScienceComputer Science (R0)