Deep Clustering of Remote Sensing Scenes through Heterogeneous Transfer Learning
This work addresses the problem of clustering unlabeled remote sensing imagery for domain-specific applications, but it is incremental as it builds on existing transfer learning and clustering techniques.
The paper tackles unsupervised clustering of remote sensing scenes without labels by using heterogeneous transfer learning, finetuning a pretrained network, and applying manifold projection and Bayesian clustering, and demonstrates that it outperforms state-of-the-art zero-shot classification methods on several datasets.
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.