This work addresses the problem of semi-supervised image classification task with the integration of several effective self-supervised pretext tasks. Different from widely-used consistency regularization within semi-supervised learning, we explored a novel self-supervised semi-supervised learning framework Color-S4L especially with image colorization surrogate task and deeply evaluate performances of more various neural architectures in such special pipeline. Also, we demonstrate its effectiveness and optimal performance on CIFAR-10, SVHN and CIFAR-100 datasets in comparison to previous supervised and semi-supervised methods.
Continued to update the whole code.