Prototype-Based Pseudo-Label Denoising for Source-Free Domain Adaptation in Remote Sensing Semantic Segmentation
This addresses domain shift in remote sensing image analysis, but it is incremental as it builds on existing source-free adaptation techniques.
The paper tackles the problem of noisy pseudo-labels in source-free domain adaptation for remote sensing semantic segmentation, proposing a prototype-guided framework that improves performance over existing methods.
Source-Free Domain Adaptation (SFDA) enables domain adaptation for semantic segmentation of Remote Sensing Images (RSIs) using only a well-trained source model and unlabeled target domain data. However, the lack of ground-truth labels in the target domain often leads to the generation of noisy pseudo-labels. Such noise impedes the effective mitigation of domain shift (DS). To address this challenge, we propose ProSFDA, a prototype-guided SFDA framework. It employs prototype-weighted pseudo-labels to facilitate reliable self-training (ST) under pseudo-labels noise. We, in addition, introduce a prototype-contrast strategy that encourages the aggregation of features belonging to the same class, enabling the model to learn discriminative target domain representations without relying on ground-truth supervision. Extensive experiments show that our approach substantially outperforms existing methods.