CSDL Home W WACV-MOTION 2005 Applications of Computer Vision and the IEEE Workshop on Motion and Video Computing, IEEE Workshop on
Jan. 5, 2005 to Jan. 7, 2005
Chuck Rosenberg , Google, Inc., Mountain View, CA
Martial Hebert , Carnegie Mellon University, Pittsburgh, PA
Henry Schneiderman , Carnegie Mellon University, Pittsburgh, PA
The construction of appearance-based object detection systems is time-consuming and difficult because a large number of training examples must be collected and manually labeled in order to capture variations in object appearance. Semi-supervised training is a means for reducing' the effort needed to prepare the training set by training the model with a small number of fully labeled examples and an additional set of unlabeled or weakly labeled examples. In this work we present a semi-supervised approach to training object detection systems based on self-training. we implement our approach as a wrapper around the training process of an existing object detector and present empirical results. The key contributions of this empirical study is to demonstrate that a model trained in this manner can achieve results comparable to a model trained in the traditional manner using a much larger set of fully labeled data, and that a training data selection metric that is defined independently of the detector greatly outperforms a selection metric based on the detection confidence generated by the detector.
Chuck Rosenberg, Martial Hebert, Henry Schneiderman, "Semi-Supervised Self-Training of Object Detection Models", WACV-MOTION, 2005, Applications of Computer Vision and the IEEE Workshop on Motion and Video Computing, IEEE Workshop on, Applications of Computer Vision and the IEEE Workshop on Motion and Video Computing, IEEE Workshop on 2005, pp. 29-36, doi:10.1109/ACVMOT.2005.107