Incremental zero-shot learning based on attributes for image classification

Instead of assuming a closed-world environment comprising a fixed number of objects, modern pattern recognition systems need to recognize outliers, identify anomalies, or discover entirely new objects, which is known as zero-shot object recognition. However, many existing zero-shot learning methods are not efficient enough to incrementally update themselves with new samples mixed with known or novel class labels. In this paper, we propose an incremental zero-shot learning framework (IIAP/QR) based on indirect-attribute-prediction (IAP) model. Firstly, a fast incremental classifier based on null space based linear discriminant analysis with QR-updating (NLDA/QR) is put forward, which can solve small-sample-size (SSS) problem and unequal-sample-size (USS) problem that usually occur in incremental learning using the centroid of each class as input. Then with the probabilistic inference of Class-Attribute layer and Attribute-Zero shot classification layer, IIAP/QR model can efficiently update itself for the insertion of both new samples to the existing class and totally novel classes with comparable recognition accuracy for zero-shot object recognition.

[1]  Yoshua Bengio,et al.  Zero-data Learning of New Tasks , 2008, AAAI.

[2]  Josef Kittler,et al.  Incremental Linear Discriminant Analysis Using Sufficient Spanning Set Approximations , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

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

[4]  Frédéric Jurie,et al.  Improving Semantic Embedding Consistency by Metric Learning for Zero-Shot Classiffication , 2016, ECCV.

[5]  Venkatesh Saligrama,et al.  Zero-Shot Learning via Semantic Similarity Embedding , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[6]  Hui Xiong,et al.  IDR/QR: an incremental dimension reduction algorithm via QR decomposition , 2004, IEEE Transactions on Knowledge and Data Engineering.

[7]  Hanqing Lu,et al.  Solving the small sample size problem of LDA , 2002, Object recognition supported by user interaction for service robots.

[8]  G. Stewart,et al.  Reorthogonalization and stable algorithms for updating the Gram-Schmidt QR factorization , 1976 .

[9]  Venkatesh Saligrama,et al.  Zero-Shot Learning via Joint Latent Similarity Embedding , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

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

[12]  Adriana Kovashka,et al.  Relative Attributes for Enhanced Human-Machine Communication , 2012, AAAI.

[13]  Delin Chu,et al.  A new and fast implementation for null space based linear discriminant analysis , 2010, Pattern Recognit..

[14]  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.

[15]  Wei-Lun Chao,et al.  Synthesized Classifiers for Zero-Shot Learning , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Xiaoou Li,et al.  Data Stream Classification for Structural Health Monitoring via On-Line Support Vector Machines , 2015, 2015 IEEE First International Conference on Big Data Computing Service and Applications.

[17]  Chaomin Luo,et al.  L3-SVM: a lifelong learning method for SVM , 2015, 2015 International Joint Conference on Neural Networks (IJCNN).

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

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