Denoising autoencoder with modulated lateral connections learns invariant representations of natural images
@article{Rasmus2015DenoisingAW, title={Denoising autoencoder with modulated lateral connections learns invariant representations of natural images}, author={Antti Rasmus and T. Raiko and H. Valpola}, journal={CoRR}, year={2015}, volume={abs/1412.7210} }
Suitable lateral connections between encoder and decoder are shown to allow higher layers of a denoising autoencoder (dAE) to focus on invariant representations. In regular autoencoders, detailed information needs to be carried through the highest layers but lateral connections from encoder to decoder relieve this pressure. It is shown that abstract invariant features can be translated to detailed reconstructions when invariant features are allowed to modulate the strength of the lateral… CONTINUE READING
Figures, Tables, and Topics from this paper
Paper Mentions
17 Citations
Lateral Connections in Denoising Autoencoders Support Supervised Learning
- Computer Science, Mathematics
- ArXiv
- 2015
- 18
- PDF
Learning from minimally labeled data with accelerated convolutional neural networks
- Computer Science
- 2016
Theta-RBM: Unfactored Gated Restricted Boltzmann Machine for Rotation-Invariant Representations
- Computer Science
- ArXiv
- 2016
- 1
- Highly Influenced
- PDF
BLAN: Bi-directional ladder attentive network for facial attribute prediction
- Computer Science
- Pattern Recognit.
- 2020
- PDF
Unsupervised Rotation Factorization in Restricted Boltzmann Machines
- Computer Science, Medicine
- IEEE Transactions on Image Processing
- 2020
- 2
- Highly Influenced
- PDF
A semi-supervised convolutional neural network for hyperspectral image classification
- Computer Science
- 2017
- 62
References
SHOWING 1-10 OF 25 REFERENCES
Extracting and composing robust features with denoising autoencoders
- Mathematics, Computer Science
- ICML '08
- 2008
- 4,354
- PDF
Gradient-based learning of higher-order image features
- Computer Science
- 2011 International Conference on Computer Vision
- 2011
- 65
- PDF
ImageNet classification with deep convolutional neural networks
- Computer Science
- Commun. ACM
- 2012
- 59,714
- PDF
Emergence of Phase- and Shift-Invariant Features by Decomposition of Natural Images into Independent Feature Subspaces
- Mathematics, Computer Science
- Neural Computation
- 2000
- 596
- PDF
Learning Multiple Layers of Features from Tiny Images
- Computer Science
- 2009
- 10,524
- Highly Influential
- PDF
Emergence of simple-cell receptive field properties by learning a sparse code for natural images
- Computer Science, Medicine
- Nature
- 1996
- 5,352
- PDF