Learning Hypergraph-regularized Attribute Predictors

We present a novel attribute learning framework named Hypergraph-based Attribute Predictor (HAP). In HAP, a hypergraph is leveraged to depict the attribute relations in the data. Then the attribute prediction problem is casted as a regularized hypergraph cut problem, in which a collection of attribute projections is jointly learnt from the feature space to a hypergraph embedding space aligned with the attributes. The learned projections directly act as attribute classifiers (linear and kernelized). This formulation leads to a very efficient approach. By considering our model as a multi-graph cut task, our framework can flexibly incorporate other available information, in particular class label. We apply our approach to attribute prediction, Zero-shot and N-shot learning tasks. The results on AWA, USAA and CUB databases demonstrate the value of our methods in comparison with the state-of-the-art approaches.

[1]  Kristen Grauman,et al.  Decorrelating Semantic Visual Attributes by Resisting the Urge to Share , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Babak Saleh,et al.  Write a Classifier: Zero-Shot Learning Using Purely Textual Descriptions , 2013, 2013 IEEE International Conference on Computer Vision.

[3]  Shih-Fu Chang,et al.  Designing Category-Level Attributes for Discriminative Visual Recognition , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Yuxiao Hu,et al.  Face recognition using Laplacianfaces , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Cordelia Schmid,et al.  Label-Embedding for Attribute-Based Classification , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Mikhail Belkin,et al.  Laplacian Eigenmaps for Dimensionality Reduction and Data Representation , 2003, Neural Computation.

[7]  Bernt Schiele,et al.  Evaluating knowledge transfer and zero-shot learning in a large-scale setting , 2011, CVPR 2011.

[8]  Christoph H. Lampert,et al.  Learning to detect unseen object classes by between-class attribute transfer , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Yang Wang,et al.  A Discriminative Latent Model of Object Classes and Attributes , 2010, ECCV.

[10]  Stephen Lin,et al.  Graph Embedding and Extensions: A General Framework for Dimensionality Reduction , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Kristen Grauman,et al.  Inferring Analogous Attributes , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Jieping Ye,et al.  Multi-label Multiple Kernel Learning , 2008, NIPS.

[13]  Bernhard Schölkopf,et al.  Learning with Hypergraphs: Clustering, Classification, and Embedding , 2006, NIPS.

[14]  Qingshan Liu,et al.  Image retrieval via probabilistic hypergraph ranking , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[15]  Shaogang Gong,et al.  Transductive Multi-view Embedding for Zero-Shot Recognition and Annotation , 2014, ECCV.

[16]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[17]  Larry S. Davis,et al.  Image ranking and retrieval based on multi-attribute queries , 2011, CVPR 2011.

[18]  Ahmed M. Elgammal,et al.  On The Effect of Hyperedge Weights On Hypergraph Learning , 2014, Image Vis. Comput..

[19]  Xiaoyang Tan,et al.  Exploiting relationship between attributes for improved face verification , 2014, Comput. Vis. Image Underst..

[20]  Christoph H. Lampert,et al.  Attribute-Based Classification for Zero-Shot Visual Object Categorization , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Bernt Schiele,et al.  Transfer Learning in a Transductive Setting , 2013, NIPS.

[22]  Devi Parikh,et al.  Attributes for Classifier Feedback , 2012, ECCV.

[23]  Trevor Darrell,et al.  DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition , 2013, ICML.

[24]  Leonid Sigal,et al.  A Unified Semantic Embedding: Relating Taxonomies and Attributes , 2014, NIPS.

[25]  Kristen Grauman,et al.  Relative attributes , 2011, 2011 International Conference on Computer Vision.

[26]  Vinod Nair,et al.  A joint learning framework for attribute models and object descriptions , 2011, 2011 International Conference on Computer Vision.

[27]  Tao Xiang,et al.  Learning Multimodal Latent Attributes , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[28]  Jieping Ye,et al.  Hypergraph spectral learning for multi-label classification , 2008, KDD.

[29]  Ali Farhadi,et al.  Describing objects by their attributes , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

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

[31]  Kristen Grauman,et al.  Zero-shot recognition with unreliable attributes , 2014, NIPS.

[32]  Christoph H. Lampert,et al.  Augmented Attribute Representations , 2012, ECCV.

[33]  Bernhard Schölkopf,et al.  A Generalized Representer Theorem , 2001, COLT/EuroCOLT.

[34]  Babak Saleh,et al.  Heterogeneous Domain Adaptation : Learning Visual Classifiers from Textual Description , 2013 .

[35]  Xiaodong Yu,et al.  Attribute-Based Transfer Learning for Object Categorization with Zero/One Training Example , 2010, ECCV.

[36]  Jitendra Malik,et al.  Normalized cuts and image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[37]  Gang Chen,et al.  Efficient multi-label classification with hypergraph regularization , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[38]  C. Lawrence Zitnick,et al.  Zero-Shot Learning via Visual Abstraction , 2014, ECCV.