Visual categorization with negative examples for free

Automatic visual categorization is critically dependent on labeled examples for supervised learning. As an alternative to traditional expert labeling, social-tagged multimedia is becoming a novel yet subjective and inaccurate source of learning examples. Different from existing work focusing on collecting positive examples, we study in this paper the potential of substituting social tagging for expert labeling for creating negative examples. We present an empirical study using 6.5 million Flickr photos as a source of social tagging. Our experiments on the PASCAL VOC challenge 2008 show that with a relative loss of only 4.3% in terms of mean average precision, expert-labeled negative examples can be completely replaced by social-tagged negative examples for consumer photo categorization.

[1]  Marcel Worring,et al.  Learning tag relevance by neighbor voting for social image retrieval , 2008, MIR '08.

[2]  Rong Yan,et al.  Semantic concept-based query expansion and re-ranking for multimedia retrieval , 2007, ACM Multimedia.

[3]  Shih-Fu Chang,et al.  To search or to label?: predicting the performance of search-based automatic image classifiers , 2006, MIR '06.

[4]  Markus Koch,et al.  Learning TRECVID'08 High-Level Features from YouTube , 2008, TRECVID.

[5]  Fei-Fei Li,et al.  OPTIMOL: Automatic Online Picture Collection via Incremental Model Learning , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Xian-Sheng Hua,et al.  Online multi-label active annotation: towards large-scale content-based video search , 2008, ACM Multimedia.

[7]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[8]  Rong Yan,et al.  Negative pseudo-relevance feedback in content-based video retrieval , 2003, MULTIMEDIA '03.

[9]  Laura A. Dabbish,et al.  Labeling images with a computer game , 2004, AAAI Spring Symposium: Knowledge Collection from Volunteer Contributors.

[10]  Jianguo Zhang,et al.  The PASCAL Visual Object Classes Challenge , 2006 .

[11]  Robert P. W. Duin,et al.  Uniform Object Generation for Optimizing One-class Classifiers , 2002, J. Mach. Learn. Res..

[12]  Keiji Yanai,et al.  Probabilistic web image gathering , 2005, MIR '05.

[13]  Arnold W. M. Smeulders,et al.  Real-time bag of words, approximately , 2009, CIVR '09.