Efficient Unsupervised Learning for Plankton Images

TL;DR

This paper introduces an efficient unsupervised learning pipeline for classifying plankton images, leveraging a VAE-based feature extraction and clustering, significantly outperforming existing methods.

Contribution

The paper presents a novel unsupervised classification method using a VAE on features from a pre-trained network, improving accuracy over traditional approaches.

Findings

Outperforms state-of-the-art unsupervised methods on multiple plankton datasets.

Uses a two-step feature extraction and clustering pipeline.

Provides more accurate and meaningful image embeddings.

Abstract

Monitoring plankton populations in situ is fundamental to preserve the aquatic ecosystem. Plankton microorganisms are in fact susceptible of minor environmental perturbations, that can reflect into consequent morphological and dynamical modifications. Nowadays, the availability of advanced automatic or semi-automatic acquisition systems has been allowing the production of an increasingly large amount of plankton image data. The adoption of machine learning algorithms to classify such data may be affected by the significant cost of manual annotation, due to both the huge quantity of acquired data and the numerosity of plankton species. To address these challenges, we propose an efficient unsupervised learning pipeline to provide accurate classification of plankton microorganisms. We build a set of image descriptors exploiting a two-step procedure. First, a Variational Autoencoder (VAE) is trained on features extracted by a pre-trained neural network. We then use the learnt latent space as image descriptor for clustering. We compare our method with state-of-the-art unsupervised approaches, where a set of pre-defined hand-crafted features is used for clustering of plankton images. The proposed pipeline outperforms the benchmark algorithms for all the plankton datasets included in our analysis, providing better image embedding properties.