Learning Discriminative Reconstructions for Unsupervised Outlier Removal

Yan Xia, Xudong Cao, Fang Wen, Gang Hua, Jian Sun; The IEEE International Conference on Computer Vision (ICCV), 2015, pp. 1511-1519

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.

Related Material


[pdf]
[bibtex]
@InProceedings{Xia_2015_ICCV,
author = {Xia, Yan and Cao, Xudong and Wen, Fang and Hua, Gang and Sun, Jian},
title = {Learning Discriminative Reconstructions for Unsupervised Outlier Removal},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {December},
year = {2015}
}