AIBullisharXiv โ CS AI ยท Mar 117/10
๐ง
BiCLIP: Domain Canonicalization via Structured Geometric Transformation
Researchers introduce BiCLIP, a new framework that improves vision-language models' ability to adapt to specialized domains through geometric transformations. The approach achieves state-of-the-art results across 11 benchmarks while maintaining simplicity and low computational requirements.