FDS: Feedback-guided Domain Synthesis with Multi-Source Conditional Diffusion Models for Domain Generalization
This work addresses domain generalization for improving model robustness against distribution shifts, representing an incremental advancement through novel synthesis techniques.
The paper tackles the problem of limited control and diversity in domain generalization by proposing FDS, a feedback-guided domain synthesis method using diffusion models to generate novel pseudo-domains, which sets new benchmarks in performance across challenging datasets.
Domain Generalization techniques aim to enhance model robustness by simulating novel data distributions during training, typically through various augmentation or stylization strategies. However, these methods frequently suffer from limited control over the diversity of generated images and lack assurance that these images span distinct distributions. To address these challenges, we propose FDS, Feedback-guided Domain Synthesis, a novel strategy that employs diffusion models to synthesize novel, pseudo-domains by training a single model on all source domains and performing domain mixing based on learned features. By incorporating images that pose classification challenges to models trained on original samples, alongside the original dataset, we ensure the generation of a training set that spans a broad distribution spectrum. Our comprehensive evaluations demonstrate that this methodology sets new benchmarks in domain generalization performance across a range of challenging datasets, effectively managing diverse types of domain shifts. The code can be found at: \url{https://github.com/Mehrdad-Noori/FDS.git}.