Skip to content

Youzhihui/PDLCD

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 

Repository files navigation

Prototype Discriminative Learning for Semi-Supervised Change Detection in Remote Sensing Images

This project contains the implementation of our work for change detection: Prototype Discriminative Learning for Semi-Supervised Change Detection in Remote Sensing Images

News

Repo is created in 2023-07-14. Code will come soon.

Abstract

With the continuous progress of deep learning in remote sensing (RS) visual tasks, considerable advancements have been achieved in RS image change detection (CD). However, prevailing CD methods heavily rely on extensive sets of fully pixel-wise hand-annotated training data, a time-consuming and costly process, and they fail to fully harness the potential benefits of deep feature representations within the deep feature domain. To tackle the mentioned issues, we propose a novel semi-supervised CD method called PDLCD, which strategically leverages useful information from massive unlabeled data to complement labeled data with just a few samples. Specifically, changed objects and unchanged backgrounds of bi-temporal RS images are complex and fickle, our approach advocates dividing each category into multiple sub-classes in the deep feature domain. In this scheme, the high-level feature of each sub-class follows a Gaussian distribution. Then, prototype discriminative learning (PDL) is introduced to explicitly encourage deep features of samples closer to the nearest prototype within their respective category, and away from all prototypes of other categories. We design feature discriminative loss (FDL) to implement PDL for constructing more pronounced intra-class compactness and inter-class variability. Finally, we compute the supervised loss based on a limited set of labeled data, incorporate the unsupervised loss leveraging a substantial volume of unlabeled data, and include FDL within the deep feature domain to collectively optimize the model. Extensive experiments carried out on three challenging RS image CD datasets illustrate that our proposed semi-supervised CD method obtains better CD performance than previous counterparts.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published