Abstract
Automatic category discovery from images is a challenging problem in computer vision community especially from natural scene images due to the great variability in them. This paper proposes a novel context-aware topic model for category discovery in complex natural scenes. The proposed model constructs a generative probabilistic procedure from three-level features consisting of patch, region and the entire image by introducing latent topic variables to every patch and every region. Additionally, a new kind of scene context prior, namely, the spatial preference of categories, is also modeled using only a few parameters to reduce the ambiguity of categories in scene images. By regarding “topics” as “categories”, category discovery is thus converted to the inference of the proposed probabilistic model, which will further be addressed under a Gibbs-EM framework effectively. Experimental results on two benchmark datasets comprising MSRC-v2 and SIFT Flow show its effectiveness and the advantages comparing with other methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Russell, B.C., Freeman, W.T., Efros, A.A., Sivic, J., Zisserman, A.: Using multiple segmentations to discover objects and their extent in image collections. In: CVPR, vol. 2, pp. 1605–1614 (2006)
Wang, X., Grimson, E.: Spatial latent dirichlet allocation. In: NIPS (2007)
Cao, L., Li, F.F.: Spatially coherent latent topic model for concurrent segmentation and classification of objects and scenes. In: ICCV, pp. 1–8 (2007)
Zhao, B., Fei-Fei, L., Xing, E.P.: Image segmentation with topic random field. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 785–798. Springer, Heidelberg (2010)
Lin, D., Xiao, J.: Characterizing layouts of outdoor scenes using spatial topic processes. In: ICCV, pp. 841–848 (2013)
Liu, D., Chen, T.: Unsupervised image categorization and object localization using topic models and correspondences between images. In: ICCV, pp. 1–7 (2007)
Liu, D., Chen, T.: Semantic-shift for unsupervised object detection. In: CVPR (2006)
Fergus, R., Li, F.F., Perona, P., Zisserman, A.: Learning object categories from internet image searches. Proc. IEEE 98, 1453–1466 (2010)
Lee, Y.J., Grauman, K.: Shape discovery from unlabeled image collections. In: CVPR, pp. 2254–2261 (2009)
Lee, Y.J., Grauman, K.: Foreground focus: unsupervised learning from partially matching images. Int. J. Comput. Vis. 85, 143–166 (2009)
Kim, G., Faloutsos, C., Hebert, M.: Unsupervised modeling of object categories using link analysis techniques. In: CVPR (2008)
Lee, Y.J., Grauman, K.: Object-graphs for context-aware visual category discovery. IEEE Trans. Pattern Anal. Mach. Intell. 34, 346–358 (2012)
Lee, Y.J., Grauman, K.: Learning the easy things first: self-paced visual category discovery. In: CVPR, pp. 1721–1728 (2011)
Tuytelaars, T., Lampert, C.H., Blaschko, M.B., Buntine, W.L.: Unsupervised object discovery: a comparison. Int. J. Comput. Vis. 88, 284–302 (2010)
Shotton, J., Winn, J.M., Rother, C., Criminisi, A.: Textonboost for image understanding: multi-class object recognition and segmentation by jointly modeling texture, layout, and context. Int. J. Comput. Vis. 81, 2–23 (2009)
Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation. J. Mach. Learn. Res. 3, 993–1022 (2003)
Niu, Z., Hua, G., Gao, X., Tian, Q.: Context aware topic model for scene recognition. In: CVPR, pp. 2743–2750 (2012)
Oliva, A., Torralba, A.: Modeling the shape of the scene: a holistic representation of the spatial envelope. Int. J. Comput. Vis. 42, 145–175 (2001)
Torralba, A.: Contextual priming for object detection. Int. J. Comput. Vis. 53, 169–191 (2003)
Andrieu, C., de Freitas, N., Doucet, A., Jordan, M.I.: An introduction to mcmc for machine learning. Mach. Learn. 50, 5–43 (2003)
Tighe, J., Lazebnik, S.: Superparsing - scalable nonparametric image parsing with superpixels. Int. J. Comput. Vis. 101, 329–349 (2013)
Su, H., Sun, M., Li, F.F., Savarese, S.: Learning a dense multi-view representation for detection, viewpoint classification and synthesis of object categories. In: ICCV, pp. 213–220 (2009)
Li, L.J., Socher, R., Li, F.F.: Towards total scene understanding: classification, annotation and segmentation in an automatic framework. In: CVPR, pp. 2036–2043 (2009)
Niu, Z., Hua, G., Gao, X., Tian, Q.: Spatial-disclda for visual recognition. In: CVPR, pp. 1769–1776 (2011)
Rubinstein, M., Joulin, A., Kopf, J., Liu, C.: Unsupervised joint object discovery and segmentation in internet images. In: CVPR, pp. 1939–1946 (2013)
Zhu, J.Y., Wu, J., Wei, Y., Chang, E.I.C., Tu, Z.: Unsupervised object class discovery via saliency-guided multiple class learning. In: CVPR, pp. 3218–3225 (2012)
Yuan, Z., Lu, T., Shivakumara, P.: A novel topic-level random walk framework for scene image co-segmentation. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part I. LNCS, vol. 8689, pp. 695–709. Springer, Heidelberg (2014)
Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Süsstrunk, S.: Slic superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Pattern Anal. Mach. Intell. 34, 2274–2282 (2012)
Acknowledgement
The work described in this paper was supported by the Natural Science Foundation of China under Grant No. 61272218 and No. 61321491, the 973 Program of China under Grant No. 2010CB327903, and the Program for New Century Excellent Talents under NCET-11-0232.
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
Yuan, Z., Lu, T. (2015). A Novel Context-Aware Topic Model for Category Discovery in Natural Scenes. In: Cremers, D., Reid, I., Saito, H., Yang, MH. (eds) Computer Vision -- ACCV 2014. ACCV 2014. Lecture Notes in Computer Science(), vol 9006. Springer, Cham. https://doi.org/10.1007/978-3-319-16817-3_11
Download citation
DOI: https://doi.org/10.1007/978-3-319-16817-3_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-16816-6
Online ISBN: 978-3-319-16817-3
eBook Packages: Computer ScienceComputer Science (R0)