Unsupervised Robust Feature-Based Partition Ensembling to Discover Categories

The design of novel robust image descriptors is still a formidable problem. Different features, with different capabilities, are introduced every year. However, to explore how to combine them is also a fundamental task. This paper proposes two novel strategies for aggregating different featurebased image partitions to tackle the challenging problem of discovering objects in unlabeled image collections. Inspired by consensus clustering models, we introduce the Aggregated Partition (AP) approach, which, starting from a set of weak input partitions, builds a final partition where the disagreements with the input partitions are optimized. We then generalize the AP formulation and derive the Selective AP, which automatically identifies the subset of features and partitions that further improves the precision of the final partition. Experiments on three challenging datasets show how our methods are able to consistently outperform competing methods, reporting state-of-the-art results.

[1]  Luc Van Gool,et al.  Ensemble Partitioning for Unsupervised Image Categorization , 2012, ECCV.

[2]  Michael I. Jordan,et al.  On Spectral Clustering: Analysis and an algorithm , 2001, NIPS.

[3]  Andreas Krause,et al.  Discriminative Clustering by Regularized Information Maximization , 2010, NIPS.

[4]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.

[5]  Aristides Gionis,et al.  Clustering Aggregation , 2005, ICDE.

[6]  Joachim M. Buhmann,et al.  Stability-Based Validation of Clustering Solutions , 2004, Neural Computation.

[7]  Trevor Darrell,et al.  Unsupervised Learning of Categories from Sets of Partially Matching Image Features , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[8]  Boris Babenko,et al.  Weakly Supervised Object Localization with Stable Segmentations , 2008, ECCV.

[9]  Antonio Torralba,et al.  Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope , 2001, International Journal of Computer Vision.

[10]  Venkatesan Guruswami,et al.  Clustering with qualitative information , 2005, 44th Annual IEEE Symposium on Foundations of Computer Science, 2003. Proceedings..

[11]  Sinisa Todorovic,et al.  From a Set of Shapes to Object Discovery , 2010, ECCV.

[12]  Andrew Zisserman,et al.  Image Classification using Random Forests and Ferns , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[13]  George Michailidis,et al.  Critical limitations of consensus clustering in class discovery , 2014, Scientific Reports.

[14]  Carla E. Brodley,et al.  Solving cluster ensemble problems by bipartite graph partitioning , 2004, ICML.

[15]  Michal Irani,et al.  “Clustering by Composition”—Unsupervised Discovery of Image Categories , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Gary R. Bradski,et al.  A codebook-free and annotation-free approach for fine-grained image categorization , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  G. Griffin,et al.  Caltech-256 Object Category Dataset , 2007 .

[18]  Cordelia Schmid,et al.  Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[19]  Antonio Torralba,et al.  Semi-Supervised Learning in Gigantic Image Collections , 2009, NIPS.

[20]  Joydeep Ghosh,et al.  Cluster Ensembles --- A Knowledge Reuse Framework for Combining Multiple Partitions , 2002, J. Mach. Learn. Res..

[21]  Delbert Dueck,et al.  Clustering by Passing Messages Between Data Points , 2007, Science.

[22]  Horst Bischof,et al.  Unsupervised Object Discovery and Segmentation in Videos , 2013, BMVC.

[23]  Yong Jae Lee,et al.  Object-graphs for context-aware category discovery , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[24]  Christoph H. Lampert,et al.  Unsupervised Object Discovery: A Comparison , 2010, International Journal of Computer Vision.

[25]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[26]  Gabriela Csurka,et al.  Visual categorization with bags of keypoints , 2002, eccv 2004.

[27]  Ulrike von Luxburg,et al.  Clustering Stability: An Overview , 2010, Found. Trends Mach. Learn..

[28]  Cordelia Schmid,et al.  Multi-fold MIL Training for Weakly Supervised Object Localization , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[29]  Pietro Perona,et al.  The Caltech-UCSD Birds-200-2011 Dataset , 2011 .

[30]  Fei-Fei Li,et al.  ImageNet: A large-scale hierarchical image database , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[31]  Svetlana Lazebnik,et al.  Scene recognition and weakly supervised object localization with deformable part-based models , 2011, 2011 International Conference on Computer Vision.

[32]  Cordelia Schmid,et al.  Unsupervised object discovery and localization in the wild: Part-based matching with bottom-up region proposals , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[33]  Jill P. Mesirov,et al.  Consensus Clustering: A Resampling-Based Method for Class Discovery and Visualization of Gene Expression Microarray Data , 2003, Machine Learning.

[34]  Alexei A. Efros,et al.  Discovering objects and their location in images , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[35]  Andrew Zisserman,et al.  Geometric LDA: A Generative Model for Particular Object Discovery , 2008, BMVC.

[36]  Pietro Perona,et al.  Towards automatic discovery of object categories , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[37]  Pietro Perona,et al.  Self-Tuning Spectral Clustering , 2004, NIPS.

[38]  Yihong Gong,et al.  Locality-constrained Linear Coding for image classification , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.