Object Discovery and Localization Via Structural Contrast

This paper explores structural contrast of object proposal for unsupervised object discovery. In this paper, an object proposal is considered as distinctive to the others in an image based on the structural uniqueness and distribution. A symmetric Kullback-Leibler (KL) distance metric is proposed to measure the difference between the distributions of structured edges. The computation of this distance metric is fully unsupervised, without any image level annotation or any labeling of visual semantics. Inspired by the pixel-level saliency filtering, a contrast-based saliency assignment is introduced to model the uniqueness and distribution distinctiveness of an object proposal as structural contrast. Visual objects can be discovered and localized by the proposals with the highest ranked structural contrast. Experiments evaluated on PascaiVOC07 demonstrate that the proposed unsupervised method outperforms the state-of-the-art unsupervised and weakly-supervised methods.

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

[2]  Fei-Fei Li,et al.  Object discovery in 3D scenes via shape analysis , 2013, 2013 IEEE International Conference on Robotics and Automation.

[3]  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).

[4]  Ce Liu,et al.  Unsupervised Joint Object Discovery and Segmentation in Internet Images , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Zhuowen Tu,et al.  Unsupervised object class discovery via saliency-guided multiple class learning , 2012, CVPR.

[6]  Chong Wang,et al.  Weakly Supervised Object Localization with Latent Category Learning , 2014, ECCV.

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

[8]  Vladlen Koltun,et al.  Geodesic Object Proposals , 2014, ECCV.

[9]  C. Lawrence Zitnick,et al.  Edge Boxes: Locating Object Proposals from Edges , 2014, ECCV.

[10]  Tao Xiang,et al.  In Defence of Negative Mining for Annotating Weakly Labelled Data , 2012, ECCV.

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

[12]  Fei-Fei Li,et al.  Efficient Image and Video Co-localization with Frank-Wolfe Algorithm , 2014, ECCV.

[13]  Koen E. A. van de Sande,et al.  Selective Search for Object Recognition , 2013, International Journal of Computer Vision.

[14]  Tao Xiang,et al.  Weakly supervised object detector learning with model drift detection , 2011, 2011 International Conference on Computer Vision.

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

[16]  Tao Xiang,et al.  Bayesian Joint Topic Modelling for Weakly Supervised Object Localisation , 2013, 2013 IEEE International Conference on Computer Vision.

[17]  Dieter Fox,et al.  RGB-D object discovery via multi-scene analysis , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[18]  Santiago Manen,et al.  Prime Object Proposals with Randomized Prim's Algorithm , 2013, 2013 IEEE International Conference on Computer Vision.