FrEVL: Leveraging Frozen Pretrained Embeddings for Efficient Vision-Language Understanding

The deployment of vision-language models remains constrained by substantial computational requirements. We present FrEVL, a framework exploring whether frozen pretrained embeddings can support effective vision-language understanding. Our analysis reveals that frozen embeddings contain rich information for discriminative tasks, achieving 85% to 95% of state-of-the-art performance on standard benchmarks with only 68.4M trainable parameters. This performance dichotomy reveals a critical insight: frozen embedding effectiveness depends on alignment between pretraining objectives and downstream task requirements. When accounting for end-to-end computation including embedding extraction, FrEVL provides 2.3× speedup with 52% lower energy consumption, making it suitable for scenarios with pre-computable inputs or when deployment constraints outweigh marginal performance gains. Our evaluation provides practitioners with guidance on when frozen embedding approaches represent viable alternatives to full model deployment. We will release our complete implementation and evaluation framework to facilitate further research into efficient multi-modal understanding.