Learning Discriminative Reconstructions for Unsupervised Outlier Removal
Abstract
We study the problem of automatically removing outliers from noisy data, with application for removing outlier images from an image collection. We address this problem by utilizing the reconstruction errors of an autoencoder. We observe that when data are reconstructed from low-dimensional representations, the inliers and the outliers can be well separated according to their reconstruction errors. Based on this basic observation, we gradually inject discriminative information in the learning process of an autoencoder to make the inliers and the outliers more separable. Experiments on a variety of image datasets validate our approach.
Cite
Text
Xia et al. "Learning Discriminative Reconstructions for Unsupervised Outlier Removal." International Conference on Computer Vision, 2015. doi:10.1109/ICCV.2015.177Markdown
[Xia et al. "Learning Discriminative Reconstructions for Unsupervised Outlier Removal." International Conference on Computer Vision, 2015.](https://mlanthology.org/iccv/2015/xia2015iccv-learning/) doi:10.1109/ICCV.2015.177BibTeX
@inproceedings{xia2015iccv-learning,
title = {{Learning Discriminative Reconstructions for Unsupervised Outlier Removal}},
author = {Xia, Yan and Cao, Xudong and Wen, Fang and Hua, Gang and Sun, Jian},
booktitle = {International Conference on Computer Vision},
year = {2015},
doi = {10.1109/ICCV.2015.177},
url = {https://mlanthology.org/iccv/2015/xia2015iccv-learning/}
}