Záznam dôkazov metódy

Masked Autoencoders

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.

Sources recorded, not reviewed

Zdrojový záznam

Citácie skopírované doslovne zo zdrojového záznamu metódy. Nevyplýva z nich žiadne overenie na úrovni tvrdenia.

Masked Autoencoders are Scalable Vision Learners

Taxonomický záznam metódy · ml-model / deep-learning

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). · DOI 10.1109/CVPR52688.2022.01553

Otvoriť celú metódu

Spracované tvrdenia

Tvrdenia uložené v registri dôkazov, každé s vlastným hodnotením.

Zatiaľ žiadne spracované tvrdenia

Tento pohľad nevymýšľa hodnotenie tvrdenia, ak register žiadne nemá.

Súvisiace metódy

Vygenerované z grafu metód a zobrazené ako vzťahy navrhnuté strojom – nevyplýva z nich žiadne tvrdenie o dôkaze.

Same method familyLatent Diffusion Modelsmachine-suggested · Relational suggestion, not evidence.Same method familySimCLRmachine-suggested · Relational suggestion, not evidence.Same method familySwin Transformermachine-suggested · Relational suggestion, not evidence.Same method familyVision Transformermachine-suggested · Relational suggestion, not evidence.