Joint probability estimation of attribute chain for zero-shot learning

Zero-shot learning (ZSL) aims to classify the objects without any training samples. Direct Attribute Prediction (DAP) gives a solution with attribute space but it makes the assumption of attribute independence. To relax this assumption and consider the relation among attributes, Joint Attribute Chain Prediction (JACP) algorithm is proposed in this paper. It estimates the joint probability of attribute chain by the multiplication formula without the independence assumption. To deal with the difficulty of estimation, clustering algorithm of attributes is presented to generate several independent attribute sets. Each set trains a series of classifiers to calculate the joint probability individually and then the posteriori of classes can be obtained. Experiments on AwA and aPascal-aYahoo data sets demonstrate the effectiveness of our algorithm.

[1]  Kiriakos N. Kutulakos.  Trends and Topics in Computer Vision , 2010, Lecture Notes in Computer Science.

[2]  Satoshi Oyama,et al.  Image Classification by Transfer Learning Based on the Predictive Ability of Each Attribute , 2014 .

[3]  K. Dembczynski,et al.  On Label Dependence in Multi-Label Classification , 2010 .

[4]  Eyke Hüllermeier,et al.  Bayes Optimal Multilabel Classification via Probabilistic Classifier Chains , 2010, ICML.

[5]  Daoqiang Zhang,et al.  Attribute relation learning for zero-shot classification , 2014, Neurocomputing.

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

[7]  Fei-Fei Li,et al.  Attribute Learning in Large-Scale Datasets , 2010, ECCV Workshops.

[8]  Ali Farhadi,et al.  Describing objects by their attributes , 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]  Qiang Ji,et al.  A Unified Probabilistic Approach Modeling Relationships between Attributes and Objects , 2013, 2013 IEEE International Conference on Computer Vision.

[11]  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.

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

[13]  Eyke Hüllermeier,et al.  On label dependence in multilabel classification , 2010, ICML 2010.

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

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

[16]  Bernt Schiele,et al.  Combining Language Sources and Robust Semantic Relatedness for Attribute-Based Knowledge Transfer , 2010, ECCV Workshops.

[17]  Aram Kawewong,et al.  Online incremental attribute-based zero-shot learning , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[18]  Hanhui Li,et al.  BAP: Bimodal Attribute Prediction for Zero-Shot Image Categorization , 2014, ACM Multimedia.

[19]  Chee Seng Chan,et al.  pLSA-based zero-shot learning , 2013, 2013 IEEE International Conference on Image Processing.