1 code implementation • 13 Jun 2023 • Aakash Mishra, Rajat Mittal, Christy Jestin, Kostas Tingos, Pranav Rajpurkar
We hypothesize that domain pre-trained models such as CXR-BERT, BlueBERT, and ClinicalBERT offer the potential to improve the performance of CLIP-like models with specific domain knowledge by replacing BERT weights at the cost of breaking the original model's alignment.