Simple Sparsification Improves Sparse Denoising Autoencoders in Denoising Highly Corrupted Images

Kyunghyun Cho
Proceedings of the 30th International Conference on Machine Learning, PMLR 28(3):432-440, 2013.

Abstract

Recently Burger et al. (2012) and Xie et al. (2012) proposed to use a denoising autoencoder (DAE) for denoising noisy images. They showed that a plain, deep DAE can denoise noisy images as well as the conventional methods such as BM3D and KSVD. Both of them approached image denoising by denoising small, image patches of a larger image and combining them to form a clean image. In this setting, it is usual to use the encoder of the DAE to obtain the latent representation and subsequently apply the decoder to get the clean patch. We propose that a simple sparsification of the latent representation found by the encoder improves denoising performance, when the DAE was trained with sparsity regularization. The experiments confirm that the proposed sparsification indeed helps both denoising a small image patch and denoising a larger image consisting of those patches. Furthermore, it is found out that the proposed method improves even classification performance when test samples are corrupted with noise.

Cite this Paper

BibTeX
@InProceedings{pmlr-v28-cho13, title = {Simple Sparsification Improves Sparse Denoising Autoencoders in Denoising Highly Corrupted Images}, author = {Cho, Kyunghyun}, booktitle = {Proceedings of the 30th International Conference on Machine Learning}, pages = {432--440}, year = {2013}, editor = {Dasgupta, Sanjoy and McAllester, David}, volume = {28}, number = {3}, series = {Proceedings of Machine Learning Research}, address = {Atlanta, Georgia, USA}, month = {17--19 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v28/cho13.pdf}, url = {https://proceedings.mlr.press/v28/cho13.html}, abstract = {Recently Burger et al. (2012) and Xie et al. (2012) proposed to use a denoising autoencoder (DAE) for denoising noisy images. They showed that a plain, deep DAE can denoise noisy images as well as the conventional methods such as BM3D and KSVD. Both of them approached image denoising by denoising small, image patches of a larger image and combining them to form a clean image. In this setting, it is usual to use the encoder of the DAE to obtain the latent representation and subsequently apply the decoder to get the clean patch. We propose that a simple sparsification of the latent representation found by the encoder improves denoising performance, when the DAE was trained with sparsity regularization. The experiments confirm that the proposed sparsification indeed helps both denoising a small image patch and denoising a larger image consisting of those patches. Furthermore, it is found out that the proposed method improves even classification performance when test samples are corrupted with noise.} }
Endnote
%0 Conference Paper %T Simple Sparsification Improves Sparse Denoising Autoencoders in Denoising Highly Corrupted Images %A Kyunghyun Cho %B Proceedings of the 30th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2013 %E Sanjoy Dasgupta %E David McAllester %F pmlr-v28-cho13 %I PMLR %P 432--440 %U https://proceedings.mlr.press/v28/cho13.html %V 28 %N 3 %X Recently Burger et al. (2012) and Xie et al. (2012) proposed to use a denoising autoencoder (DAE) for denoising noisy images. They showed that a plain, deep DAE can denoise noisy images as well as the conventional methods such as BM3D and KSVD. Both of them approached image denoising by denoising small, image patches of a larger image and combining them to form a clean image. In this setting, it is usual to use the encoder of the DAE to obtain the latent representation and subsequently apply the decoder to get the clean patch. We propose that a simple sparsification of the latent representation found by the encoder improves denoising performance, when the DAE was trained with sparsity regularization. The experiments confirm that the proposed sparsification indeed helps both denoising a small image patch and denoising a larger image consisting of those patches. Furthermore, it is found out that the proposed method improves even classification performance when test samples are corrupted with noise.
RIS
TY - CPAPER TI - Simple Sparsification Improves Sparse Denoising Autoencoders in Denoising Highly Corrupted Images AU - Kyunghyun Cho BT - Proceedings of the 30th International Conference on Machine Learning DA - 2013/05/26 ED - Sanjoy Dasgupta ED - David McAllester ID - pmlr-v28-cho13 PB - PMLR DP - Proceedings of Machine Learning Research VL - 28 IS - 3 SP - 432 EP - 440 L1 - http://proceedings.mlr.press/v28/cho13.pdf UR - https://proceedings.mlr.press/v28/cho13.html AB - Recently Burger et al. (2012) and Xie et al. (2012) proposed to use a denoising autoencoder (DAE) for denoising noisy images. They showed that a plain, deep DAE can denoise noisy images as well as the conventional methods such as BM3D and KSVD. Both of them approached image denoising by denoising small, image patches of a larger image and combining them to form a clean image. In this setting, it is usual to use the encoder of the DAE to obtain the latent representation and subsequently apply the decoder to get the clean patch. We propose that a simple sparsification of the latent representation found by the encoder improves denoising performance, when the DAE was trained with sparsity regularization. The experiments confirm that the proposed sparsification indeed helps both denoising a small image patch and denoising a larger image consisting of those patches. Furthermore, it is found out that the proposed method improves even classification performance when test samples are corrupted with noise. ER -
APA
Cho, K.. (2013). Simple Sparsification Improves Sparse Denoising Autoencoders in Denoising Highly Corrupted Images. Proceedings of the 30th International Conference on Machine Learning, in Proceedings of Machine Learning Research 28(3):432-440 Available from https://proceedings.mlr.press/v28/cho13.html.

Related Material