Domain-Aware Fine-Tuning of Foundation Models
Ugur Ali Kaplan, Margret Keuper, Anna Khoreva, Dan Zhang, Yumeng Li · arXiv (Cornell University) · 2024
Foundation models (FMs) have revolutionized computer vision, enabling effective learning across different domains. However, their performance under domain shift is yet underexplored. This paper investigates the zero-shot domain adaptation potential of FMs by comparing different backbone architectures and introducing novel domain-aware components that leverage domain related textual embeddings. We propose domain adaptive normalization, termed as Domino, which explicitly leverages domain embeddings during fine-tuning, thus making the model domain aware. Ultimately, Domino enables more robust computer vision models that can adapt effectively to various unseen domains.