• by homarp on 7/20/2020, 6:49:17 PM

    "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

  • by phenkdo on 7/20/2020, 9:20:26 PM

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