Weakly supervised discriminative localization and classification: a joint learning process

Minh Hoai Nguyen, Lorenzo Torresani, Fernando De la Torre Frade, and Carsten Rother
Proceedings of International Conference on Computer Vision (ICCV), October, 2009.


Download
  • Adobe portable document format (pdf) (417KB)
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.

Abstract
Visual categorization problems, such as object classification or action recognition, are increasingly often approached using a detection strategy: a classifier function is first applied to candidate subwindows of the image or the video, and then the maximum classifier score is used for class decision. Traditionally, the subwindow classifiers are trained on a large collection of examples manually annotated with masks or bounding boxes. The reliance on time-consuming human labeling effectively limits the application of these methods to problems involving very few categories. Furthermore, the human selection of the masks introduces arbitrary biases (e.g. in terms of window size and location) which may be suboptimal for classification. In this paper we propose a novel method for learning a discriminative subwindow classifier from examples annotated with binary labels indicating the presence of an object or action of interest, but not its location. During training, our approach simultaneously localizes the instances of the positive class and learns a subwindow SVM to recognize them. We extend our method to classification of time series by presenting an algorithm that localizes the most discriminative set of temporal segments in the signal. We evaluate our approach on several datasets for object and action recognition and show that it achieves results similar and in many cases superior to those obtained with full supervision.

Keywords
Image Classification, Image Categorization, Time series classification, Object Detection, Object Localization, Support Vector Machines

Notes
Sponsor: U.S. Naval Research Laboratory
Number of pages: 8
Note: Portions of this work were performed whileMinh Hoai Nguyen and Lorenzo Torresani were at Microsoft Research Cambridge.

Text Reference
Minh Hoai Nguyen, Lorenzo Torresani, Fernando De la Torre Frade, and Carsten Rother, "Weakly supervised discriminative localization and classification: a joint learning process," Proceedings of International Conference on Computer Vision (ICCV), October, 2009.

BibTeX Reference
@inproceedings{Nguyen_2009_6401,
   author = "Minh Hoai Nguyen and Lorenzo Torresani and Fernando {De la Torre Frade} and Carsten Rother",
   title = "Weakly supervised discriminative localization and classification: a joint learning process",
   booktitle = "Proceedings of International Conference on Computer Vision (ICCV)",
   month = "October",
   year = "2009",
   Notes = "Portions of this work were performed whileMinh Hoai Nguyen and Lorenzo Torresani were at Microsoft Research Cambridge."
}