FastMAE: Efficient masked autoencoder with offline tokenizer
Masked autoencoders (MAEs) have recently achieved great success in computer vision. They can automatically extract representations from unlabeled data and improve the performance of various downstream tasks. However, training an MAE model requires substantial resources, which limits their accessibil...
Na minha lista:
| Principais autores: | , , , |
|---|---|
| Format: | Artigo |
| Sprog: | Inglês |
| Udgivet: |
Tsinghua University Press
2025-06-01
|
| Serier: | Computational Visual Media |
| Fag: | |
| Online adgang: | https://www.sciopen.com/article/10.26599/CVM.2025.9450474 |
| Tags: |
Ingen Tags, Vær først til at tagge denne postø!
|