Filtering Specialized Change in a Few-Shot Setting

Martin Hermann, Sudipan Saha, Xiao Xiang Zhu

Research output: Contribution to journalArticlepeer-review

5 Scopus citations

Abstract

The aim of change detection in remote sensing usually is not to find all differences between the observations, but rather only specific types of change, such as urban development, deforestation, or even more specialized categories like roadwork. However, often there are no large public datasets available for very fine-grained tasks, and to collect the amount of training data needed for most supervised learning methods is very costly and often prohibitive. For this reason, we formulate the problem of few-shot filtering, where we are provided with a relatively large change detection dataset and, at test time, a few instances of one particular change type that we try to 'filter out' of the learned changes. For example, we might train on data of general urban change, and, given some samples of building construction, aim to only predict instances of these on the test set, all without any explicit labels for buildings in the training data. We further investigate a fine-Tuning approach to this problem and assess its performance on a public dataset that we adapt to be used in this novel setting.

Original languageEnglish
Pages (from-to)1185-1196
Number of pages12
JournalIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Volume16
DOIs
StatePublished - 2023

Keywords

  • Change detection
  • deep learning
  • few-shot filtering
  • few-shot learning

Fingerprint

Dive into the research topics of 'Filtering Specialized Change in a Few-Shot Setting'. Together they form a unique fingerprint.

Cite this