ABSTRACT
This paper describes a method to learn Bag-Of-Words (BOW) descriptor for image representation which is robust to domain shift. Domain shift is necessary when a classifier trained on one dataset (source) is applied for classification on a different dataset (target). Datasets acquired with different conditions, have dissimilar feature distributions among them. Traditional method for representing each image by a BOW descriptor with the vocabulary learnt on a reference dataset does not work well for such cross-dataset tasks. We propose a new method to learn an amended dictionary composed of class specific atoms. The proposed Domain-Invariant BOW (DI-BOW) descriptor built from this dictionary has much better class discriminability and inherently attenuates domain-specific characteristics, making it more suitable to cross-domain tasks. Results based on DI-BOW descriptor reveal its efficiency, by outperforming state-of-the-art domain adaptation techniques for object recognition.
- M. Aharon, M. Elad, and A. Bruckstein. K-svd: An algorithm for designing overcomplete dictionaries for sparse representation. IEEE Transactions on Signal Processing, 54(11):4311--4322, 2006. Google ScholarDigital Library
- M. Bacchiani and B. Roark. Unsupervised language model adaptation. In Conference on Acoustics, Speech, and Signal Processing, volume 1, pages I--224, 2003.Google ScholarCross Ref
- M. Baktashmotlagh, M. Harandi, B. Lovell, and M. Salzmann. Unsupervised domain adaptation by domain invariant projection. In IEEE International Conference on Computer Vision, pages 769--776, 2013. Google ScholarDigital Library
- H. Bay, A. Ess, T. Tuytelaars, and L. Van Gool. Speeded-up robust features (SURF). Computer Vision Image Understanding, 110(3):346--359, 2008. Google ScholarDigital Library
- O. Boiman, E. Shechtman, and M. Irani. In defense of nearest-neighbor based image classification. In International Conference on Computer Vision and Pattern Recognition, pages 1--8, 2008.Google ScholarCross Ref
- H. Daume III. Frustratingly easy domain adaptation. In Annual Meeting of the Association of Computational Linguistics, pages 256--263, 2007.Google Scholar
- L. Duan, D. Xu, I. W. Tsang, and J. Luo. Visual event recognition in videos by learning from web data. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(9):1667--1680, 2012. Google ScholarDigital Library
- B. Fernando, A. Habrard, M. Sebban, and T. Tuytelaars. Unsupervised visual domain adaptation using subspace alignment. In International Conference in Computer Vision, 2013. Google ScholarDigital Library
- B. Gong, Y. Shi, F. Sha, and K. Grauman. Geodesic flow kernel for unsupervised domain adaptation. In IEEE International Conference on Computer Vision and Pattern Recognition, pages 2066--2073, 2012. Google ScholarDigital Library
- R. Gopalan, R. Li, and R. Chellappa. Domain adaptation for object recognition: An unsupervised approach. In IEEE International Conference on Computer Vision, pages 999--1006, 2011. Google ScholarDigital Library
- A. Gretton, A. Smola, J. Huang, M. Schmittfull, K. Borgwardt, and B. Schölkopf. Covariate shift by kernel mean matching. Dataset shift in machine learning, Chap. 8, Cambridge: MIT Press, pages 131--160, 2009.Google Scholar
- V. Jain and E. G. Learned-Miller. Online domain adaptation of a pre-trained cascade of classifiers. In CVPR, pages 577--584, 2011. Google ScholarDigital Library
- A. Khosla, T. Zhou, T. Malisiewicz, A. Efros, and A. Torralba. Undoing the damage of dataset bias. In European Conference on Computer Vision, pages 158--171, 2012. Google ScholarDigital Library
- S. Lazebnik, C. Schmid, and J. Ponce. Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In International Conference on Computer Vision and Pattern Recognition, volume 2, pages 2169--2178, 2006. Google ScholarDigital Library
- S. J. Pan, I. Tsang, J. Kwok, and Q. Yang. Domain adaptation via transfer component analysis. IEEE Transactions on Neural Networks, 22(2):199--210, 2011. Google ScholarDigital Library
- S. J. Pan and Q. Yang. A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22:1345--1359, 2010. Google ScholarDigital Library
- K. Saenko, B. Kulis, M. Fritz, and T. Darrell. Adapting visual category models to new domains. In European Conference on Computer Vision, pages 213--226, 2010. Google ScholarDigital Library
- J. Sivic, B. C. Russell, A. A. Efros, A. Zisserman, and W. T. Freeman. Discovering objects and their location in images. In International Conference on Computer Vision, pages 370--377, 2005. Google ScholarDigital Library
- M. Sugiyama, S. Nakajima, H. Kashima, P. von Bünau, and M. Kawanabe. Direct importance estimation with model selection and its application to covariate shift adaptation. In Neural Information Processing Systems, pages 1962--1965, 2007.Google Scholar
- T. Tommasi and B. Caputo. Frustratingly easy NBNN domain adaptation. In International Conference on Computer Vision, pages 897--904, 2013. Google ScholarDigital Library
- A. Torralba and A. A. Efros. Unbiased look at dataset bias. In International Conference on Computer Vision and Pattern Recognition, pages 1521--1528, 2011. Google ScholarDigital Library
- I. Tosic and P. Frossard. Dictionary learning. Signal Processing Magazine, IEEE, 28(2):27--38, March 2011.Google ScholarCross Ref
- J. Yang, R. Yan, and A. G. Hauptmann. Cross-domain video concept detection using adaptive svms. In International Conference on Multimedia, pages 188--197, 2007. Google ScholarDigital Library
Index Terms
- DI-BOW: Domain Invariant Feature Descriptor Using Bag of Words
Recommendations
HSOG: a novel local descriptor based on histograms of second order gradients for object categorization
ICMR '13: Proceedings of the 3rd ACM conference on International conference on multimedia retrievalThis paper presents a novel local image descriptor for object categorization that extracts the Histograms of the Second Order Gradients and is thereby named as HSOG. The HSOG descriptor is in contrast to the widely used ones in the literature, e.g. SIFT,...
Object Categorization Using Hierarchical Wavelet Packet Texture Descriptors
ISM '09: Proceedings of the 2009 11th IEEE International Symposium on MultimediaObject categorization plays an important role in computer vision, semantic based image content understanding, and image retrieval. Wavelet packet transform provides a very good observation for the images by sub-band filtering. Different objects have ...
Evaluation of local features and classifiers in BOW model for image classification
Bag-of-word (BOW) is used in many state-of-the-art methods of image classification, and it is especially suitable for multi-class classification. Many kinds of local features and classifiers are applicable for the BOW model. However, it is unclear which ...
Comments