Color-$S^{4}L$: Self-supervised Semi-supervised Learning with Image Colorization
This work addresses semi-supervised learning for image classification, offering a novel framework that improves performance on standard benchmarks.
The paper tackled semi-supervised image classification by integrating self-supervised pretext tasks, particularly image colorization, and demonstrated optimal performance on CIFAR-10, SVHN, and CIFAR-100 datasets compared to previous methods.
This work addresses the problem of semi-supervised image classification tasks 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-$S^{4}L$) especially with image colorization proxy task and deeply evaluate performances of various network architectures in such special pipeline. Also, we demonstrated its effectiveness and optimal performance on CIFAR-10, SVHN and CIFAR-100 datasets in comparison to previous supervised and semi-supervised optimal methods.