BibTex format

author = {Creswell, A and Bharath, AA},
doi = {10.1109/TNNLS.2018.2852738},
journal = {IEEE Transactions on Neural Networks and Learning Systems},
pages = {968--984},
title = {Denoising adversarial autoencoders},
url = {},
volume = {30},
year = {2019}

RIS format (EndNote, RefMan)

AB - Unsupervised learning is of growing interest becauseit unlocks the potential held in vast amounts of unlabelled data tolearn useful representations for inference. Autoencoders, a formof generative model, may be trained by learning to reconstructunlabelled input data from a latent representation space. Morerobust representations may be produced by an autoencoderif it learns to recover clean input samples from corruptedones. Representations may be further improved by introducingregularisation during training to shape the distribution of theencoded data in the latent space. We suggestdenoising adversarialautoencoders, which combine denoising and regularisation, shap-ing the distribution of latent space using adversarial training.We introduce a novel analysis that shows how denoising maybe incorporated into the training and sampling of adversarialautoencoders. Experiments are performed to assess the contri-butions that denoising makes to the learning of representationsfor classification and sample synthesis. Our results suggest thatautoencoders trained using a denoising criterion achieve higherclassification performance, and can synthesise samples that aremore consistent with the input data than those trained withouta corruption process.
AU - Creswell,A
AU - Bharath,AA
DO - 10.1109/TNNLS.2018.2852738
EP - 984
PY - 2019///
SN - 2162-2388
SP - 968
TI - Denoising adversarial autoencoders
T2 - IEEE Transactions on Neural Networks and Learning Systems
UR -
UR -
UR -
VL - 30
ER -