Abstract
Many computer vision methods rely on annotated image sets without taking advantage of the increasing number of unlabeled images available. This paper explores an alternative approach involving unsupervised structure discovery and semi-supervised learning (SSL) in image collections. Focusing on object classes, the first part of the paper contributes with an extensive evaluation of state-of-the-art image representations. Thus, it underlines the decisive influence of the local neighborhood structure and its direct consequences on SSL results and the importance of developing powerful object representations. In a second part, we propose and explore promising directions to improve results by looking at the local topology between images and feature combination strategies.
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.
This work was supported by a Google Research Award.
Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
References
Chum, O., Perdoch, M., Matas, J.: Geometric min-hashing: Finding a (thick) needle in a haystack. In: CVPR (2009)
Sivic, J., Russell, B., Zisserman, A., Freeman, W., Efros, A.: Unsupervised discovery of visual object class hierarchies. In: CVPR (2008)
Vijayanarasimhan, S., Grauman, K.: Keywords to visual categories: Multiple-instance learning for weakly supervised object categorization. In: CVPR (2008)
Li, L.-J., Fei-Fei, L.: Optimol: Automatic online picture collection via incremental model learning. IJCV (2009)
Vijayanarasimhan, S., Grauman, K.: Multi-level active prediction of useful image annotations for recognition. In: NIPS (2008)
Russell, B., Torralba, A., Murphy, K., Freeman, W.: LabelMe: A database and web-based tool for image annotation. IJCV (2008)
Verbeek, J., Triggs, B.: Scene segmentation with CRFs learned from partially labeled images. In: NIPS, vol. 20 (2008)
Fergus, R., Perona, P., Zisserman, A.: Weakly supervised scale-invariant learning of models for visual recognition. IJCV (2007)
Leistner, C., Saffari, A., Santner, J., Bischof, H.: Semi-supervised random forests. In: ICCV (2009)
Saffari, A., Leistner, C., Bischof, H.: Regularized multi-class semi-supervised boosting. In: CVPR (2009)
Fergus, R., Weiss, Y., Torralba, A.: Semi-supervised learning in gigantic image collections. In: NIPS (2009)
Chapelle, O., Schölkopf, B., Zien, A. (eds.): Semi-Supervised Learning. MIT Press, Cambridge (2006)
Zhou, D., Bousquet, O., Lal, T.N., Weston, J., Schölkopf, B.: Learning with local and global consistency. In: NIPS (2004)
Zhu, X., Ghahramani, Z., Lafferty, J.: Semi-supervised learning using gaussian fields and harmonic functions. In: ICML (2003)
Liu, W., Chang, S.: Robust multi-class transductive learning with graphs. In: CVPR (2009)
Leibe, B., Schiele, B.: Analyzing appearance and contour based methods for object categorization. In: CVPR (2003)
Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL VOC Challenge 2008 Results (2008)
Lampert, C., Nickisch, H., Harmeling, S.: Learning to detect unseen object classes by between-class attribute transfer. In: CVPR (2009)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR (2005)
Oliva, A., Torralba, A.: Modeling the shape of the scene: A holistic representation of the spatial envelope. IJCV (2001)
Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: CVPR (2006)
Wolf, L., Hassner, T., Taigman, Y.: Descriptor based methods in the wild. In: ECCV (2008)
Mikolajczyk, K., Schmid, C.: Scale & affine invariant interest point detectors. IJCV (2004)
Lowe, D.: Distinctive image features from scale-invariant keypoints. IJCV (2004)
van de Sande, K., Gevers, T., Snoek, C.: Evaluating color descriptors for object and scene recognition. PAMI (2010)
Hein, M., Maier, M.: Manifold denoising. In: NIPS (2006)
Bengio, Y., Delalleau, O., Le Roux, N.: Label propagation and quadratic criterion. In: [12]
Zhou, D., Huang, J., Schöhkopf, B.: Learning from labeled and unlabeled data on a directed graph. In: ICML (2005)
Perronnin, F., Liu, Y., Renders, J.: A family of contextual measures of similarity between distributions with application to image retrieval. In: CVPR (2009)
Gehler, P., Nowozin, S.: On feature combination for multiclass object classification. In: CVPR (2009)
Zhu, X.: Semi-supervised learning literature survey. Technical report, UW (2005)
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
Ebert, S., Larlus, D., Schiele, B. (2010). Extracting Structures in Image Collections for Object Recognition. In: Daniilidis, K., Maragos, P., Paragios, N. (eds) Computer Vision – ECCV 2010. ECCV 2010. Lecture Notes in Computer Science, vol 6311. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15549-9_52
Download citation
DOI: https://doi.org/10.1007/978-3-642-15549-9_52
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-15548-2
Online ISBN: 978-3-642-15549-9
eBook Packages: Computer ScienceComputer Science (R0)