vision-language models Papers - Abhik | ML & CV Consultant

2023

BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models

Computer Vision Natural Language Processing Deep Learning Multimodal Learning BLIP-2 Vision-Language Models

Introducing BLIP-2, a new vision-language model that leverages frozen image encoders and large language models to achieve improved efficiency and performance in various multimodal tasks.

Read review Original Paper

vision-language models

Papers Related to vision-language models

BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models