Abstract
This paper introduces a new approach, called reverse training, to efficiently extend binary classifiers for the task of multi-class image set classification. Unlike existing binary to multi-class extension strategies, which require multiple binary classifiers, the proposed approach is very efficient since it trains a single binary classifier to optimally discriminate the class of the query image set from all others. For this purpose, the classifier is trained with the images of the query set (labelled positive) and a randomly sampled subset of the training data (labelled negative). The trained classifier is then evaluated on rest of the training images. The class of these images with their largest percentage classified as positive is predicted as the class of the query image set. The confidence level of the prediction is also computed and integrated into the proposed approach to further enhance its robustness and accuracy. Extensive experiments and comparisons with existing methods show that the proposed approach achieves state of the art performance for face and object recognition on a number of datasets. © 2014 Springer International Publishing.
Original language | English |
---|---|
Title of host publication | Computer Vision – ECCV 2014. ECCV 2014. Lecture Notes in Computer Science |
Place of Publication | Switzerland |
Publisher | Springer |
Pages | 784-799 |
Volume | 8694 LNCS |
ISBN (Print) | 9783319105987 |
DOIs | |
Publication status | Published - 2014 |
Event | 13th European Conference on Computer Vision - Zurich, Switzerland Duration: 6 Sep 2014 → 12 Sep 2014 Conference number: 13 |
Conference
Conference | 13th European Conference on Computer Vision |
---|---|
Abbreviated title | ECCV |
Country/Territory | Switzerland |
City | Zurich |
Period | 6/09/14 → 12/09/14 |