Unsupervised Multi-Class Co-Segmentation via Joint-Cut Over $L_{1}$ -Manifold Hyper-Graph of Discriminative Image Regions

This paper systematically advocates a robust and efficient unsupervised multi-class co-segmentation approach by leveraging underlying subspace manifold propagation to exploit the cross-image coherency. It can combat certain image co-segmentation difficulties due to viewpoint change, partial occlusion, complex background, transient illumination, and cluttering texture patterns. Our key idea is to construct a powerful hyper-graph joint-cut framework, which incorporates mid-level image regions-based intra-image feature representation and $L_{1}$ -manifold graph-based inter-image coherency exploration. For local image region generation, we propose a bi-harmonic distance distribution difference metric to govern the super-pixel clustering in a bottom-up way. It not only affords drastic data reduction but also gives rise to discriminative and structure meaningful feature representation. As for the inter-image coherency, we leverage multi-type features involved $L_{1}$ -graph to detect the underlying local manifold from cross-image regions. As a result, the implicit supervising information could be encoded into the unsupervised hyper-graph joint-cut framework. We conduct extensive experiments and make comprehensive evaluations with other state-of-the-art methods over various benchmarks, including iCoseg, MSRC, and Oxford flower. All the results demonstrate the superiorities of our method in terms of accuracy, robustness, efficiency, and versatility.

[1]  Jia Xu,et al.  Analyzing the Subspace Structure of Related Images: Concurrent Segmentation of Image Sets , 2012, ECCV.

[2]  Vikas Singh,et al.  Scale invariant cosegmentation for image groups , 2011, CVPR 2011.

[3]  C. V. Jawahar,et al.  Blocks That Shout: Distinctive Parts for Scene Classification , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Jean Ponce,et al.  Discriminative clustering for image co-segmentation , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[5]  Rujie Liu,et al.  Semi-supervised Learning for Large Scale Image Cosegmentation , 2013, 2013 IEEE International Conference on Computer Vision.

[6]  Ligang Liu,et al.  Co‐Segmentation of 3D Shapes via Subspace Clustering , 2012, Comput. Graph. Forum.

[7]  Shuicheng Yan,et al.  Efficient Subspace Segmentation via Quadratic Programming , 2011, AAAI.

[8]  Shuicheng Yan,et al.  Learning With $\ell ^{1}$-Graph for Image Analysis , 2010, IEEE Transactions on Image Processing.

[9]  Andrew Blake,et al.  Cosegmentation of Image Pairs by Histogram Matching - Incorporating a Global Constraint into MRFs , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[10]  Michal Irani,et al.  Co-segmentation by Composition , 2013, 2013 IEEE International Conference on Computer Vision.

[11]  Daniel Cohen-Or,et al.  Unsupervised co-segmentation of a set of shapes via descriptor-space spectral clustering , 2011, ACM Trans. Graph..

[12]  Nikos Paragios,et al.  Graph commute times for image representation , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Larry S. Davis,et al.  Representing Videos Using Mid-level Discriminative Patches , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[14]  Matthieu Guillaumin,et al.  Segmentation Propagation in ImageNet , 2012, ECCV.

[15]  Andrew Blake,et al.  GeoS: Geodesic Image Segmentation , 2008, ECCV.

[16]  King Ngi Ngan,et al.  A Co-Saliency Model of Image Pairs , 2011, IEEE Transactions on Image Processing.

[17]  Alexei A. Efros,et al.  Unsupervised Discovery of Mid-Level Discriminative Patches , 2012, ECCV.

[18]  Xuelong Li,et al.  Query-Adaptive Reciprocal Hash Tables for Nearest Neighbor Search , 2016, IEEE Transactions on Image Processing.

[19]  Ehsan Elhamifar,et al.  Sparse subspace clustering , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[20]  YanShuicheng,et al.  Learning with l1-graph for image analysis , 2010 .

[21]  Nanning Zheng,et al.  Joint Segmentation and Recognition of Categorized Objects From Noisy Web Image Collection , 2014, IEEE Transactions on Image Processing.

[22]  Shuicheng Yan,et al.  Multi-task low-rank affinity pursuit for image segmentation , 2011, 2011 International Conference on Computer Vision.

[23]  C. Dyer,et al.  Half-integrality based algorithms for cosegmentation of images , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[24]  King Ngi Ngan,et al.  Feature Adaptive Co-Segmentation by Complexity Awareness , 2013, IEEE Transactions on Image Processing.

[25]  Hongsheng Li,et al.  A hierarchical image clustering cosegmentation framework , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

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

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

[28]  Xianglong Liu,et al.  Multiple feature kernel hashing for large-scale visual search , 2014, Pattern Recognit..

[29]  Nikos Paragios,et al.  Unsupervised co-segmentation through region matching , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[30]  Ronen Basri,et al.  Contour-based joint clustering of multiple segmentations , 2011, CVPR 2011.

[31]  Takeo Kanade,et al.  Distributed cosegmentation via submodular optimization on anisotropic diffusion , 2011, 2011 International Conference on Computer Vision.

[32]  Shang-Hong Lai,et al.  From co-saliency to co-segmentation: An efficient and fully unsupervised energy minimization model , 2011, CVPR 2011.

[33]  Hongliang Li,et al.  Repairing Bad Co-Segmentation Using Its Quality Evaluation and Segment Propagation , 2014, IEEE Transactions on Image Processing.

[34]  Francesc Moreno-Noguer,et al.  Deformation and illumination invariant feature point descriptor , 2011, CVPR 2011.

[35]  Vikas Singh,et al.  An efficient algorithm for Co-segmentation , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[36]  Jing Liu,et al.  Object co-segmentation via discriminative low rank matrix recovery , 2013, ACM Multimedia.

[37]  Koen E. A. van de Sande,et al.  Evaluating Color Descriptors for Object and Scene Recognition , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[38]  Eric P. Xing,et al.  On multiple foreground cosegmentation , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[39]  Xiaochun Cao,et al.  Cluster-Based Co-Saliency Detection , 2013, IEEE Transactions on Image Processing.

[40]  Jean Ponce,et al.  Multi-class cosegmentation , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[41]  Aimin Hao,et al.  Unsupervised Co-segmentation of Complex Image Set via Bi-harmonic Distance Governed Multi-level Deformable Graph Clustering , 2013, 2013 IEEE International Symposium on Multimedia.

[42]  Vladimir Kolmogorov,et al.  Object cosegmentation , 2011, CVPR 2011.

[43]  Subhransu Maji,et al.  Part Discovery from Partial Correspondence , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[44]  José Mario Martínez,et al.  Nonmonotone Spectral Projected Gradient Methods on Convex Sets , 1999, SIAM J. Optim..

[45]  Andrew Blake,et al.  "GrabCut" , 2004, ACM Trans. Graph..

[46]  Thomas A. Funkhouser,et al.  Biharmonic distance , 2010, TOGS.

[47]  S. Frick,et al.  Compressed Sensing , 2014, Computer Vision, A Reference Guide.