Deep Clustering of Remote Sensing Scenes through Heterogeneous Transfer Learning

TL;DR

This paper introduces a novel unsupervised clustering method for remote sensing images that leverages transfer learning, dimensionality reduction, and Bayesian clustering to effectively group unlabeled scenes, outperforming existing zero-shot classification techniques.

Contribution

The paper presents a new approach combining pretrained deep neural networks, manifold projection, and Bayesian nonparametric clustering for heterogeneous transfer learning in remote sensing.

Findings

Outperforms state-of-the-art zero-shot classification methods

Effective clustering of unseen remote sensing scenes

Utilizes transfer learning for diverse feature distributions

Abstract

This paper proposes a method for unsupervised whole-image clustering of a target dataset of remote sensing scenes with no labels. The method consists of three main steps: (1) finetuning a pretrained deep neural network (DINOv2) on a labelled source remote sensing imagery dataset and using it to extract a feature vector from each image in the target dataset, (2) reducing the dimension of these deep features via manifold projection into a low-dimensional Euclidean space, and (3) clustering the embedded features using a Bayesian nonparametric technique to infer the number and membership of clusters simultaneously. The method takes advantage of heterogeneous transfer learning to cluster unseen data with different feature and label distributions. We demonstrate the performance of this approach outperforming state-of-the-art zero-shot classification methods on several remote sensing scene classification datasets.