Metodebevisregister

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

Kilderegister

Siteringer kopiert ordrett fra metodens kilderegister. Ingen påstandsnivåverifisering er underforstått fra dem.

Masked Autoencoders are Scalable Vision Learners

Taksonomisk metoderegister · 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

Åpne full metode

Kuraterte påstander

Påstander lagret i bevishovedboken, hver med sin egen vurdering.

Ingen kuraterte påstander ennå

Denne visningen finner ikke opp en påstandsvurdering når hovedboken ikke har noen.

Relaterte metoder

Generert fra metodegrafen og vist som maskinforslåtte relasjoner – ingen bevispåstand er underforstått.

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.