CliqueCNN: Self-supervised image representation learning

How to learn useful representation from just a bunch of unlabeled images? I will give a high-level overview of what is self-supervised learning and explain the CliqueCNN method. We will also briefly talk about a bunch of other important self-supervised learning methods Annotations for evaluation on Olympic Sports dataset Discussed papers: 1. CliqueCNN: Deep Unsupervised Exemplar Learning , 2. Deep Unsupervised Similarity Learning using Partially Ordered Sets Other self-supervised learning methods: 1. RotNet 2. Doersch et al, 3. Jigsaw 4. Wang & Gupta 5. Colorization 6. Brattoli et al.,