MACHINE LEARNING

CowMask — Data Augmentation for Self-Supervised Models

Google Research recently published CowMask — a new SOTA masking-based augmentation method. The method allows training more stable self-supervised models.

CowMask — Data Augmentation for Self-Supervised Models. Source: Arxiv

The CowMask model produces state-of-the-art results on an ImageNet dataset using 10% of the labeled data during training. At the same time, the top 5 has a model error rate of 8.76%, and the top 1 has 26.06%. Using CowMask allows you to train models with state-of-the-art quality and simpler architecture. Researchers have tested CowMask for semi-supervised training on SVHN, CIFAR-10, and CIFAR-100 datasets.

Results on CIFAR-100 test set, error rates as mean ± stdev of 5 independent runs. Source: Arxiv

Models with the proposed approach gave results comparable to state-of-the-art. The project code is available in the open repository on GitHub.

google-research/google-research

Consistency in…