Stat Cafe - Isaac Ray
Deep Clustering of Remote Sensing Scenes through Heterogeneous Transfer Learning
- Time: Monday 3/3/2025 from 11:30 AM to 12:30 PM
- Location: BLOC 457
- Sandwiches provided
Description
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.
Recording
Gallery (Photos by Samantha Williams)
