Convolutional autoencoder-based multimodal one-class classification

TL;DR

This paper introduces a deep learning method using convolutional autoencoders for multimodal one-class classification, effectively detecting anomalies in multimodal data by analyzing latent space representations.

Contribution

It presents a novel multimodal one-class classification approach leveraging joint convolutional autoencoders and explores the impact of input size and feature regularizers on performance.

Findings

Multimodal approach outperforms unimodal methods.

Feature diversity regularizers enhance classification accuracy.

Optimal input image size improves model performance.

Abstract

One-class classification refers to approaches of learning using data from a single class only. In this paper, we propose a deep learning one-class classification method suitable for multimodal data, which relies on two convolutional autoencoders jointly trained to reconstruct the positive input data while obtaining the data representations in the latent space as compact as possible. During inference, the distance of the latent representation of an input to the origin can be used as an anomaly score. Experimental results using a multimodal macroinvertebrate image classification dataset show that the proposed multimodal method yields better results as compared to the unimodal approach. Furthermore, study the effect of different input image sizes, and we investigate how recently proposed feature diversity regularizers affect the performance of our approach. We show that such regularizers improve performance.