AdaSemiCD: An Adaptive Semi-Supervised Change Detection Method Based on Pseudo-Label Evaluation

TL;DR

AdaSemiCD is an adaptive semi-supervised change detection method that leverages pseudo-label evaluation, dynamic uncertainty handling, and selective teacher updates to improve change detection accuracy with limited labeled data.

Contribution

The paper introduces AdaSemiCD, a novel adaptive semi-supervised framework that enhances pseudo-label reliability and training stability for change detection in remote sensing.

Findings

Improved change detection accuracy on LEVIR-CD, WHU-CD, and CDD datasets.

Effective handling of class imbalance and boundary confusion.

Demonstrated universality across multiple datasets.

Abstract

Change Detection (CD) is an essential field in remote sensing, with a primary focus on identifying areas of change in bi-temporal image pairs captured at varying intervals of the same region by a satellite. The data annotation process for the CD task is both time-consuming and labor-intensive. To make better use of the scarce labeled data and abundant unlabeled data, we present an adaptive dynamic semi-supervised learning method, AdaSemiCD, to improve the use of pseudo-labels and optimize the training process. Initially, due to the extreme class imbalance inherent in CD, the model is more inclined to focus on the background class, and it is easy to confuse the boundary of the target object. Considering these two points, we develop a measurable evaluation metric for pseudo-labels that enhances the representation of information entropy by class rebalancing and amplification of confusing areas to give a larger weight to prospects change objects. Subsequently, to enhance the reliability of sample-wise pseudo-labels, we introduce the AdaFusion module, which is capable of dynamically identifying the most uncertain region and substituting it with more trustworthy content. Lastly, to ensure better training stability, we introduce the AdaEMA module, which updates the teacher model using only batches of trusted samples. Experimental results from LEVIR-CD, WHU-CD, and CDD datasets validate the efficacy and universality of our proposed adaptive training framework.