MONCAE: Multi-Objective Neuroevolution of Convolutional Autoencoders
This incremental work addresses the need for faster AutoML pipelines in image compression for researchers and practitioners.
The paper tackled the problem of automatically designing convolutional autoencoders for image compression by introducing a neuroevolutionary method using a hypervolume indicator, achieving compression by a factor of over 10 while maintaining image classification performance in most tasks.
In this paper, we present a novel neuroevolutionary method to identify the architecture and hyperparameters of convolutional autoencoders. Remarkably, we used a hypervolume indicator in the context of neural architecture search for autoencoders, for the first time to our current knowledge. Results show that images were compressed by a factor of more than 10, while still retaining enough information to achieve image classification for the majority of the tasks. Thus, this new approach can be used to speed up the AutoML pipeline for image compression.