High-performance self-supervised image classification

&quot;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.&quot;<p>PyTorch code: <a href="https:&#x2F;&#x2F;github.com&#x2F;facebookresearch&#x2F;swav" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;facebookresearch&#x2F;swav</a>

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