Denoising Adversarial Autoencoders

• Published in: IEEE transaction on neural networks and learning systems Vol. 30; no. 4; pp. 968 - 984
• Main Authors: Creswell, Antonia, Bharath, Anil Anthony
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.04.2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Classification; Coding; Corruption; Data models; Data processing; Decoding; Encoding; Image analysis; Learning; Noise reduction; pattern recognition; Probabilistic logic; Regularization; Representations; semisupervised learning; Task analysis; Training; Unsupervised learning
• DOI: 10.1109/TNNLS.2018.2852738
• ISSN: 2162-237X

Unsupervised learning is of growing interest because it unlocks the potential held in vast amounts of unlabeled data to learn useful representations for inference. Autoencoders, a form of generative model, may be trained by learning to reconstruct unlabeled input data from a latent representation space. More robust representations may be produced by an autoencoder if it learns to recover clean input samples from corrupted ones. Representations may be further improved by introducing regularization during training to shape the distribution of the encoded data in the latent space. We suggest denoising adversarial autoencoders (AAEs), which combine denoising and regularization, shaping the distribution of latent space using adversarial training. We introduce a novel analysis that shows how denoising may be incorporated into the training and sampling of AAEs. Experiments are performed to assess the contributions that denoising makes to the learning of representations for classification and sample synthesis. Our results suggest that autoencoders trained using a denoising criterion achieve higher classification performance and can synthesize samples that are more consistent with the input data than those trained without a corruption process.