Unsupervised Representation Learning with Laplacian Pyramid Auto-encoders
arXiv:1801.05278
Abstract
Scale-space representation has been popular in computer vision community due to its theoretical foundation. The motivation for generating a scale-space representation of a given data set originates from the basic observation that real-world objects are composed of different structures at different scales. Hence, it's reasonable to consider learning features with image pyramids generated by smoothing and down-sampling operations. In this paper we propose Laplacian pyramid auto-encoders, a straightforward modification of the deep convolutional auto-encoder architecture, for unsupervised representation learning. The method uses multiple encoding-decoding sub-networks within a Laplacian pyramid framework to reconstruct the original image and the low pass filtered images. The last layer of each encoding sub-network also connects to an encoding layer of the sub-network in the next level, which aims to reverse the process of Laplacian pyramid generation. Experimental results showed that Laplacian pyramid benefited the classification and reconstruction performance of deep auto-encoder approaches, and batch normalization is critical to get deep auto-encoders approaches to begin learning.
arXiv comment6 pages, 3 figures
References in corpus (7)
- Adam: A Method for Stochastic Optimization
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
- Improved Regularization of Convolutional Neural Networks with Cutout
- Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
- Shake-Shake regularization
- k-Sparse Autoencoders