Self-training via Metric Learning for Source-Free Domain Adaptation of Semantic Segmentation
This addresses domain adaptation challenges in semantic segmentation for scenarios where source data is inaccessible due to privacy or IP concerns, representing an incremental improvement over existing self-training methods.
The paper tackles the problem of source-free domain adaptation for semantic segmentation by proposing a self-training method that uses a mean-teacher model with gradient weighting based on prediction reliability, assessed via proxy-based metric learning, and it demonstrates superior performance in synthetic-to-real and cross-city scenarios compared to state-of-the-art methods.
Unsupervised source-free domain adaptation methods aim to train a model for the target domain utilizing a pretrained source-domain model and unlabeled target-domain data, particularly when accessibility to source data is restricted due to intellectual property or privacy concerns. Traditional methods usually use self-training with pseudo-labeling, which is often subjected to thresholding based on prediction confidence. However, such thresholding limits the effectiveness of self-training due to insufficient supervision. This issue becomes more severe in a source-free setting, where supervision comes solely from the predictions of the pre-trained source model. In this study, we propose a novel approach by incorporating a mean-teacher model, wherein the student network is trained using all predictions from the teacher network. Instead of employing thresholding on predictions, we introduce a method to weight the gradients calculated from pseudo-labels based on the reliability of the teacher's predictions. To assess reliability, we introduce a novel approach using proxy-based metric learning. Our method is evaluated in synthetic-to-real and cross-city scenarios, demonstrating superior performance compared to existing state-of-the-art methods.