Learning Object Categories From Internet Image Searches

被引:50
作者
Fergus, Rob [1 ]
Fei-Fei, Li [2 ]
Perona, Pietro [3 ]
Zisserman, Andrew [4 ]
机构
[1] Courant Inst, Dept Comp Sci, New York, NY 10003 USA
[2] Stanford Univ, Dept Comp Sci, Stanford, CA 94305 USA
[3] CALTECH, Dept Elect Engn, Pasadena, CA 91125 USA
[4] Univ Oxford, Dept Engn Sci, Oxford OX1 3PJ, England
基金
欧洲研究理事会; 英国工程与自然科学研究理事会;
关键词
Internet image search engines; learning; object categories; recognition; unsupervised; SCALE;
D O I
10.1109/JPROC.2010.2048990
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
In this paper, we describe a simple approach to learning models of visual object categories from images gathered from Internet image search engines. The images for a given keyword are typically highly variable, with a large fraction being unrelated to the query term, and thus pose a challenging environment from which to learn. By training our models directly from Internet images, we remove the need to laboriously compile training data sets, required by most other recognition approaches-this opens up the possibility of learning object category models "on-the-fly.'' We describe two simple approaches, derived from the probabilistic latent semantic analysis (pLSA) technique for text document analysis, that can be used to automatically learn object models from these data. We show two applications of the learned model: first, to rerank the images returned by the search engine, thus improving the quality of the search engine; and second, to recognize objects in other image data sets.
引用
收藏
页码:1453 / 1466
页数:14
相关论文
共 45 条
  • [1] [Anonymous], 2004, P WORKSH STAT LEARN
  • [2] [Anonymous], 2005, P INT C COMP VIS
  • [3] Matching words and pictures
    Barnard, K
    Duygulu, P
    Forsyth, D
    de Freitas, N
    Blei, DM
    Jordan, MI
    [J]. JOURNAL OF MACHINE LEARNING RESEARCH, 2003, 3 (06) : 1107 - 1135
  • [4] Berg AC, 2005, PROC CVPR IEEE, P26
  • [5] BERG T, 2006, P INT C COMP VIS PAT, P1463
  • [6] Latent Dirichlet allocation
    Blei, DM
    Ng, AY
    Jordan, MI
    [J]. JOURNAL OF MACHINE LEARNING RESEARCH, 2003, 3 (4-5) : 993 - 1022
  • [7] BOSCH A, 2006, P ECCV, P517, DOI DOI 10.1007/11744085_40
  • [8] Carbonetto P, 2004, LECT NOTES COMPUT SC, V3021, P350
  • [9] Collins B, 2008, LECT NOTES COMPUT SC, V5302, P86, DOI 10.1007/978-3-540-88682-2_8
  • [10] Csurka G., 2004, PROC ECCV INT WORKSH