BLIP-2 模型由 Junnan Li、Dongxu Li、Silvio Savarese、Steven Hoi 在BLIP-2: Bootsrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models...
SegFormer 模型是由 Enze Xie、Wenhai Wang、Zhiding Yu、Anima Anandkumar、Jose M. Alvarez、Ping Luo 在SegFormer: Simple and Efficient Design for Semantic Segmentation with ...