Table 1. Summary of self-supervised learning pretext tasks.
No. | Authors | Category | Method |
---|---|---|---|
1 | Dosovitskiy et al. (2015) | Predictive | Exemplar CNN |
2 | Doersch, Gupta & Efros (2015) | Predictive | Relative position prediction |
3 | Noroozi & Favaro (2016) | Predictive | Jigsaw puzzle |
4 | Komodakis & Gidaris (2018) | Predictive | Rotation prediction |
5 | Vincent et al. (2008) | Generative | Denoising auto-encoder |
6 | Pathak et al. (2016) | Generative | Image inpainting |
7 | Zhang, Isola & Efros (2016) | Generative | Image colorization |
8 | Zhang, Isola & Efros (2017) | Generative | Split-brain auto-encoder |
9 | Radford, Metz & Chintala (2016) | Generative | Deep Convolutional GAN |
10 | Donahue, Krähenbühl & Darrell (2016) | Generative | Bi-directional GAN |
11 | van den Oord, Li & Vinyals (2018) | Contrastive | CPC |
12 | He et al. (2020) | Contrastive | MoCo |
13 | Chen et al. (2020) | Contrastive | SimCLR |
14 | Grill et al. (2020) | Contrastive | BYOL |
15 | Caron et al. (2020) | Contrastive | SwAV |