"For instance, our technique requires only 6 hours and 15 minutes to achieve 72.1 percent top-1 accuracy with a standard ResNet-50 on ImageNet, using 64 V100 16GB GPUs. Previous self-supervised methods required at least 6x more computing power and still achieved worse performance."

PyTorch code: https://github.com/facebookresearch/swav

Hi, this is a very interesting project. Are you considering including temporality into this? Video understanding for example.