Semi-supervised Learning of Feature Hierarchies for Object Detection in a Video

Yang Yang, Guang Shu, Mubarak Shah; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013, pp. 1650-1657

Abstract


We propose a novel approach to boost the performance of generic object detectors on videos by learning videospecific features using a deep neural network. The insight behind our proposed approach is that an object appearing in different frames of a video clip should share similar features, which can be learned to build better detectors. Unlike many supervised detector adaptation or detection-bytracking methods, our method does not require any extra annotations or utilize temporal correspondence. We start with the high-confidence detections from a generic detector, then iteratively learn new video-specific features and refine the detection scores. In order to learn discriminative and compact features, we propose a new feature learning method using a deep neural network based on auto encoders. It differs from the existing unsupervised feature learning methods in two ways: first it optimizes both discriminative and generative properties of the features simultaneously, which gives our features better discriminative ability; second, our learned features are more compact, while the unsupervised feature learning methods usually learn a redundant set of over-complete features. Extensive experimental results on person and horse detection show that significant performance improvement can be achieved with our proposed method.

Related Material


[pdf]
[bibtex]
@InProceedings{Yang_2013_CVPR,
author = {Yang, Yang and Shu, Guang and Shah, Mubarak},
title = {Semi-supervised Learning of Feature Hierarchies for Object Detection in a Video},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2013}
}