1. Eva: Exploring the limits of masked visual representation learning at scale;Fang,2022
2. Eva-clip: Improved training techniques for clip at scale;Sun,2023
3. Swin transformer v2: Scaling up capacity and resolution;Liu,2022
4. Internimage: Exploring large-scale vision foundation models with deformable convolutions;Wang,2022
5. Reversible column networks;Cai,2023