Porovnat metody

	SimCLR	Maskované autoenkodéry
Obor	Hluboké učení	Hluboké učení
Rodina	Machine learning	Machine learning
Rok vzniku	2020	2021
Tvůrce	Ting Chen	Kaiming He
Typ	Neural network architecture	Neural network architecture
Původní zdroj	Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A simple framework for contrastive learning of visual representations. In International conference on machine learning (pp. 1597-1607). PMLR.	He, K., Chen, X., Xie, S., Li, Y., Dollár, P., & Girshick, R. (2022). Masked autoencoders are scalable vision learners. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 16000-16009).
Další názvy	Simple contrastive learning, SimCLR framework	MAE, Vision MAE
Příbuzné	4	4
Shrnutí	SimCLR is a self-supervised learning framework introduced by Chen et al. in 2020 that learns visual representations by contrasting similar and dissimilar views of images. The method applies strong data augmentations to create different views of the same image, then trains an encoder to bring similar views close in representation space while pushing dissimilar views apart.	Masked Autoencoders (MAE) is a self-supervised learning approach introduced by He et al. in 2021 that masks random patches of an image and trains a model to reconstruct the missing content. Adapting the masked language modeling paradigm from NLP to vision, MAE learns rich visual representations by solving a challenging reconstruction task without requiring labels.