Unsupervised Representation Learning with Laplacian Pyramid Auto-encoders

TL;DR

This paper introduces Laplacian pyramid auto-encoders, an unsupervised deep learning method that leverages multi-scale image representations to improve feature learning, classification, and reconstruction performance.

Contribution

It proposes a novel auto-encoder architecture that incorporates Laplacian pyramids for multi-scale unsupervised feature learning, enhancing deep auto-encoder effectiveness.

Findings

Improved classification accuracy with Laplacian pyramid auto-encoders

Enhanced image reconstruction quality

Batch normalization is essential for effective learning

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.