Design a patches masked autoencoder by CNN

Enhancing Representation Learning in Masked Autoencoders by Focusing on Low-Variance Components

R-MAE: Pre-training LiDAR Perception with Masked Autoencoders for Ultra-Efficient 3D Sensing

An optimized implementation of spatiotemporal masked autoencoders

Pre-training a Masked Autoencoder with the idea of Diffusion Models for Hyperspectral Image Classification.

Investigate possibilities for Vision Transformers with multiscale grids

Train MAE on Kaggle 2 GPUs (T4x2), Log to Wandb

PyTorch wrapper for Deep Density Estimation Models

code for "AdPE: Adversarial Positional Embeddings for Pretraining Vision Transformers via MAE+"

A comprehensive (masked) graph autoencoders benchmark.

Generative modeling and representation learning through reconstruction

HSIMAE: A Unified Masked Autoencoder with large-scale pretraining for Hyperspectral Image Classification

TorchGeo: datasets, transforms, and models for geospatial data

A robust embodied navigation agent to various visual corruptions.

PyTorch implementation of MADE

The code for the paper "Contrastive Masked Autoencoders for Self-Supervised Video Hashing" (AAAI'23)

AG-MAE: Anatomically Guided Spatio-Temporal Masked Auto-Encoder for Online Hand Gesture Recognition

[TGRS 2024] PEMAE: Pixel-Wise Ensembled Masked Autoencoder for Multispectral Pan-Sharpening

"Attention, Mask, and Recommendation: A Multi-Level Graph Structure-Aware Method"