Abstract
We propose a novel approach to annotating weakly labelled data. In contrast to many existing approaches that perform annotation by seeking clusters of self-similar exemplars (minimising intra-class variance), we perform image annotation by selecting exemplars that have never occurred before in the much larger, and strongly annotated, negative training set (maximising inter-class variance). Compared to existing methods, our approach is fast, robust, and obtains state of the art results on two challenging data-sets – voc2007 (all poses), and the msr2 action data-set, where we obtain a 10% increase. Moreover, this use of negative mining complements existing methods, that seek to minimize the intra-class variance, and can be readily integrated with many of them.
Chapter PDF
Similar content being viewed by others
References
Viola, P.A., Jones, M.J.: Rapid object detection using a boosted cascade of simple features. In: CVPR, pp. 511–518 (2001)
Felzenszwalb, P., Girshick, R., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. TPAMI 32(9) (2010)
Poppe, R.: A survey on vision-based human action recognition. Image and Vision Computing 28(6), 976–990 (2010)
Weinland, D., Ronfard, R., Boyer, E.: A survey of vision-based methods for action representation, segmentation and recognition. Computer Vision and Image Understanding 115(2), 224–241 (2011)
Nguyen, M.H., Torresani, L., de la Torre, F., Rother, C.: Weakly supervised discriminative localization and classification: a joint learning process. In: ICCV, pp. 1925–1932 (2009)
Deselaers, T., Alexe, B., Ferrari, V.: Localizing Objects While Learning Their Appearance. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 452–466. Springer, Heidelberg (2010)
Pandey, M., Lazebnik, S.: Scene recognition and weakly supervised object localization with deformable part-based model. In: ICCV (2011)
Siva, P., Xiang, T.: Weakly supervised object detector learning with model drift detection. In: ICCV (2011)
Vapnik, V.N.: Statistical Learning Theory. Wiley-Interscience (1998)
Deselaers, T., Ferrari, V.: A conditional random field for multiple-instance learning. In: ICML (2010)
Maron, O., Lozano-Perez, T.: A framework for multiple-instance learning. In: NIPS (1998)
Chen, Y., Bi, J., Wang, J.: Miles: Multiple-instance learning via embedded instance selection. PAMI 28(12), 1931–1947 (2006)
Adelson, E.H.: On seeing stuff: the perception of materials by humans and machines. In: SPIE, vol. 4299, pp. 1–12 (2001)
Alexe, B., Deselaers, T., Ferrari, V.: What is an object? In: CVPR, pp. 73–80 (2010)
Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The pascal visual object classes (voc) challenge. IJCV 88(2), 303–338 (2010)
Siva, P., Xiang, T.: Weakly supervised action detection. In: BMVC (2011)
Andrews, S., Tsochantaridis, I., Hofmann, T.: Support vector machines for multiple-instance learning. In: NIPS, pp. 577–584 (2003)
Fu, Z., Robles-Kelly, A., Zhou, J.: MILIS: Multiple Instance Learning with Instance Selection. TPAMI (99) (2010)
Muja, M., Lowe, D.G.: Fast approximate nearest neighbors with automatic algorithm configuration. In: International Conference on Computer Vision Theory and Application VISSAPP 2009, pp. 331–340. INSTICC Press (2009)
Yuan, J., Liu, Z., Wu, Y.: Discriminative subvolume search for efficient action detection. In: CVPR, pp. 2442–2449 (2009)
Cao, L., Liu, Z., Huang, T.S.: Cross-data action detection. In: CVPR (2010)
Vedaldi, A., Fulkerson, B.: VLFeat: An open and portable library of computer vision algorithms (2008), http://www.vlfeat.org/
Laptev, I., Lindeberg, T.: Space-time interest points. In: ICCV, Nice, France, pp. 432–439 (2003)
Siva, P., Xiang, T.: Action detection in crowds. In: BMVC (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Siva, P., Russell, C., Xiang, T. (2012). In Defence of Negative Mining for Annotating Weakly Labelled Data. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds) Computer Vision – ECCV 2012. ECCV 2012. Lecture Notes in Computer Science, vol 7574. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33712-3_43
Download citation
DOI: https://doi.org/10.1007/978-3-642-33712-3_43
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33711-6
Online ISBN: 978-3-642-33712-3
eBook Packages: Computer ScienceComputer Science (R0)