Title :
Semi-Supervised Self-Training of Object Detection Models
Author :
Rosenberg, Chuck ; Hebert, Martial ; Schneiderman, Henry
Author_Institution :
Google, Inc., Mountain View, CA
Abstract :
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.
Keywords :
learning (artificial intelligence); object detection; object detection models; semi-supervised self-training; semi-supervised training; training data selection metric; Application software; Computer vision; Conferences; Object detection;
Conference_Titel :
Application of Computer Vision, 2005. WACV/MOTIONS '05 Volume 1. Seventh IEEE Workshops on
Conference_Location :
Breckenridge, CO
Print_ISBN :
0-7695-2271-8
DOI :
10.1109/ACVMOT.2005.107