High-performance self-supervised image classification with contrastive clustering

“We’ve developed a new technique for self-supervised training of convolutional networks commonly used for image classification and other computer vision tasks. Our method now surpasses supervised approaches on most transfer tasks, and, when compared with previous self-supervised methods, models can be trained much more quickly to achieve high performance. 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…”

Source: https://ai.facebook.com/blog/high-performance-self-supervised-image-classification-with-contrastive-clustering/

Paper: https://arxiv.org/abs/2006.09882

Code: https://github.com/facebookresearch/swav