A Particle Swarm Optimization-based Flexible Convolutional Auto-Encoder for Image Classification

TL;DR

This paper introduces a flexible convolutional auto-encoder optimized with particle swarm optimization, enabling automatic architecture discovery that outperforms existing methods in image classification tasks.

Contribution

It proposes a novel flexible convolutional auto-encoder architecture and an automatic search method using particle swarm optimization, reducing manual design effort.

Findings

Outperforms state-of-the-art algorithms on multiple datasets

Reduces computational resources needed for architecture search

Demonstrates effectiveness of PSO in neural architecture optimization

Abstract

Convolutional auto-encoders have shown their remarkable performance in stacking to deep convolutional neural networks for classifying image data during past several years. However, they are unable to construct the state-of-the-art convolutional neural networks due to their intrinsic architectures. In this regard, we propose a flexible convolutional auto-encoder by eliminating the constraints on the numbers of convolutional layers and pooling layers from the traditional convolutional auto-encoder. We also design an architecture discovery method by using particle swarm optimization, which is capable of automatically searching for the optimal architectures of the proposed flexible convolutional auto-encoder with much less computational resource and without any manual intervention. We use the designed architecture optimization algorithm to test the proposed flexible convolutional auto-encoder through utilizing one graphic processing unit card on four extensively used image classification datasets. Experimental results show that our work in this paper significantly outperform the peer competitors including the state-of-the-art algorithm.