Abstract
We propose a novel method for unsupervised class segmentation on a set of images. It alternates between segmenting object instances and learning a class model. The method is based on a segmentation energy defined over all images at the same time, which can be optimized efficiently by techniques used before in interactive segmentation. Over iterations, our method progressively learns a class model by integrating observations over all images. In addition to appearance, this model captures the location and shape of the class with respect to an automatically determined coordinate frame common across images. This frame allows us to build stronger shape and location models, similar to those used in object class detection. Our method is inspired by interactive segmentation methods [1], but it is fully automatic and learns models characteristic for the object class rather than specific to one particular object/image. We experimentally demonstrate on the Caltech4, Caltech101, and Weizmann horses datasets that our method (a) transfers class knowledge across images and this improves results compared to segmenting every image independently; (b) outperforms Grabcut [1] for the task of unsupervised segmentation; (c) offers competitive performance compared to the state-of-the-art in unsupervised segmentation and in particular it outperforms the topic model [2].
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Rother, C., Kolmogorov, V., Blake, A.: GrabCut: interactive foreground extraction using iterated graph cuts. SIGGRAPH 23, 309–314 (2004)
Cao, L., Li, F.F.: Spatially coherent latent topic model for concurrent segmentation and classification of objects and scene. In: ICCV (2007)
Boykov, Y., Jolly, M.P.: Interactive graph cuts for optimal boundary and region segmentation of objects in N-D images. In: ICCV (2001)
Lempitsky, V., Kohli, P., Rother, C., Sharp, T.: Image segmentation with a bounding box prior. In: ICCV (2009)
Schroff, F., Criminisi, A., Zisserman, A.: Object class segmentation using random forests. In: Proceedings of the British Machine Vision Conference (2008)
Shotton, J., Winn, J., Rother, C., Criminisi, A.: Textonboost for image understanding: Multi-class object recognition and segmentation by jointly modeling appearance, shape and context. IJCV 81, 2–23 (2009)
Kumar, M.P., Torr, P.H.S., Zisserman, A.: OBJ CUT. In: CVPR (2005)
Borenstein, E., Ullman, S.: Learning to segment. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3023, pp. 315–328. Springer, Heidelberg (2004)
Arora, H., Loeff, N., Forsyth, D., Ahuja, N.: Unsupervised segmentation of objects using efficient learning. In: CVPR (2007)
Winn, J., Jojic, N.: LOCUS: learning object classes with unsupervised segmentation. In: ICCV (2005)
Russell, B., Efros, A., Sivic, J., Freeman, W., Zisserman, A.: Using multiple segmentations to discover objects and their extent in image collections. In: CVPR (2006)
Todorovic, S., Ahuja, N.: Extracting subimages of an unknown category from a set of images. In: CVPR (2006)
Galleguillos, C., Babenko, B., Rabinovich, A., Belongie, S.: Weakly supervised object localization with stable segmentations. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol. 5302, pp. 193–207. Springer, Heidelberg (2008)
Kolmogorov, V., Rother, C.: Minimizing nonsubmodular functions with graph cuts – a review. PAMI 29, 1274–1279 (2007)
Kolmogorov, V.: Convergent tree-reweighted message passing for energy minimization. PAMI 28, 1568–1583 (2006)
Dalal, N., Triggs, B.: Histogram of Oriented Gradients for Human Detection. In: CVPR (2005)
Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part based models. PAMI (2009) (in press)
Alexe, B., Deselaers, T., Ferrari, V.: What is an object?. In: CVPR (2010)
Fulkerson, B., Vedaldi, A., Soatto, S.: Localizing objects with smart dictionaries. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol. 5302, pp. 179–192. Springer, Heidelberg (2008)
Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: CVPR, vol. 2, pp. 264–271 (2003)
Rother, C., Kolmogorov, V., Minka, T., Blake, A.: Cosegmentation of image pairs by histogram matching - incorporating a global constraint into MRFs. In: CVPR (2006)
Rother, C., Kolmogorov, V., Lempitsky, V., Szummer, M.: Optimizing binary MRFs via extended roof duality. In: CVPR (2007)
Csurka, G., Bray, C., Dance, C., Fan, L.: Visual categorization with bags of keypoints. In: ECCV Workshop on Stat. Learn. in: Comp. Vis. (2004)
Bay, H., Ess, A., Tuytelaars, T., van Gool, L.: SURF: Speeded up robust features. CVIU 110, 346–359 (2008)
Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. IJCV 59, 167–181 (2004)
Martin, D., Fowlkes, C., Malik, J.: Learning to detect natural image boundaries using local brightness, color and texture cues. PAMI 26, 530–549 (2003)
Fergus, R., Perona, P., Zisserman, A.: Object class recognition by unsupervised scale-invariant learning. In: CVPR (2003)
Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: An incremental Bayesian approach tested on 101 object categories. In: IEEE CVPR Workshop of Generative Model Based Vision (2004)
Lee, Y.J., Grauman, K.: Collect-cut: Segmentation with top-down cues discovered in multi-object images. In: CVPR (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Alexe, B., Deselaers, T., Ferrari, V. (2010). ClassCut for Unsupervised Class Segmentation. In: Daniilidis, K., Maragos, P., Paragios, N. (eds) Computer Vision – ECCV 2010. ECCV 2010. Lecture Notes in Computer Science, vol 6315. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15555-0_28
Download citation
DOI: https://doi.org/10.1007/978-3-642-15555-0_28
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-15554-3
Online ISBN: 978-3-642-15555-0
eBook Packages: Computer ScienceComputer Science (R0)