In recent years, masked autoencoder (MAE) has been used in various fields due to its powerful self-supervised learning ability and has achieved good results in masked data reconstruction tasks.

We also develop an efficient spike-driven Transformer architecture and a spike-masked autoencoder to prevent performance degradation ... Bo and Li, Guoqi}, journal={IEEE Transactions on Pattern ...

Several classifiers are present such as K-NN, SVM, and CNN architecture for the purpose of classification. We propose to use KNN for classification, as a simple and robust classifier for the masked ...

To overcome these limitations, we introduce AstroMAE, an innovative approach that pretrains a vision transformer encoder using a masked autoencoder method on ... subsequently fine-tuned within a ...

[pdf] H. Yu and J. Oh, "Anytime 3D Object Reconstruction Using Multi-Modal Variational Autoencoder," In: IEEE Robotics and Automation Letters, vol. 7, no. 2, pp. 2162-2169, April 2022, doi: ...

To this end, we propose a simple yet effective masked Siamese autoencoder (MSA) model, which consists of a student branch and a teacher branch. The student branch derives MAE’s advanced architecture, ...

The representation ability of the model is strongly correlated with the number of such high-quality labels. Recently, the masked autoencoder (MAE) has been shown to effectively pre-train Vision ...