Learning Discriminative Reconstructions for Unsupervised Outlier Removal

Yan Xia, Xudong Cao, Fang Wen, Gang Hua, Jian Sun
2015 2015 IEEE International Conference on Computer Vision (ICCV)  
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 lowdimensional 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
more » ... in the learning process of autoencoder to make the inliers and the outliers more separable. Experiments on a variety of image datasets validate our approach.
doi:10.1109/iccv.2015.177 dblp:conf/iccv/XiaCWHS15 fatcat:cn2dgw5ryreszc46goacx6kp5m