CLEAR: Cumulative LEARning for One-Shot One-Class Image Recognition
Abstract
This work addresses the novel problem of one-shot one-class classification. The goal is to estimate a classification decision boundary for a novel class based on a single image example. Our method exploits transfer learning to model the transformation from a representation of the input, extracted by a Convolutional Neural Network, to a classification decision boundary. We use a deep neural network to learn this transformation from a large labelled dataset of images and their associated class decision boundaries generated from ImageNet, and then apply the learned decision boundary to classify subsequent query images. We tested our approach on several benchmark datasets and significantly outperformed the baseline methods.
Cite
Text
Kozerawski and Turk. "CLEAR: Cumulative LEARning for One-Shot One-Class Image Recognition." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018. doi:10.1109/CVPR.2018.00363Markdown
[Kozerawski and Turk. "CLEAR: Cumulative LEARning for One-Shot One-Class Image Recognition." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018.](https://mlanthology.org/cvpr/2018/kozerawski2018cvpr-clear/) doi:10.1109/CVPR.2018.00363BibTeX
@inproceedings{kozerawski2018cvpr-clear,
title = {{CLEAR: Cumulative LEARning for One-Shot One-Class Image Recognition}},
author = {Kozerawski, Jedrzej and Turk, Matthew},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2018},
doi = {10.1109/CVPR.2018.00363},
url = {https://mlanthology.org/cvpr/2018/kozerawski2018cvpr-clear/}
}