| Vision-language models | ||||
| 2021 | ALIGN | Scaling Up Visual and Vision-Language Representation Learning with Noisy Text Supervision | Jia et al. | - Noisy image-text data - Constrative learning |
| 2022 | Flamingo | Flamingo: a Visual Language Model for Few-Shot Learning | Alayrac et al. | - Transformer |
| CoCa | CoCa: Contrastive Captioners are Image-Text Foundation Models | Yu et al. | - Transformer | |
| Vision transformers | ||||
| 2021 | MViT | Multiscale Vision Transformers | Fan et al. | - Transformer |
| Visual representation learning | ||||
| 2022 | BEiT | BEiT: BERT Pre-Training of Image Transformers | Bao et al. | - Transformer |
| Segmentation | ||||
| 2022 | OneFormer | OneFormer: One Transformer to Rule Universal Image Segmentation | Jain et al. | - Transformer |
| Diffusion probabilistic models | ||||
| 2023 | ControlNet | Adding Conditional Control to Text-to-Image Diffusion Models | Zhang et al. | - Transformer - Diffusion |