Physiology-Augmented Chest X-Ray Masked Autoencoder

Contains codes for paper "Self-Supervised Pretraining for Fine-Grained Plankton Recognition".

An optimized implementation of spatiotemporal masked autoencoders

Project for Computer Vision course @ MSc in Artificial Intelligence, UniVR

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

Masked Autoencoder image reconstruction app with a Streamlit interface, using PyTorch and Hugging Face model hosting for lightweight deployment.

Test Task solutions to DeepLense Projects

Self-Supervised Foundation Models for Medical Imaging — SimCLR, MoCo v3, and Masked Autoencoders pretrained on chest X-rays with few-shot evaluation

Mixture-of-Experts Masked AutoEncoder for Earth Observation.

A PyTorch implementation of Masked Autoencoders (MAE) on the STL-10 dataset, demonstrating how self-supervised learning significantly improves classification accuracy and convergence speed on limited labeled data.

Masked Multimodal Autoencoders with Contrastive Learning for Cancer Survival Prediction

Deep learning models for 3d volumetric ink detection on ancient Vesuvius scroll fragments.

TorchGeo: datasets, transforms, and models for geospatial data

Implementation of Masked AutoEncoder

Change detection on satellite images with masked autoencoders.

This repo reproduces key findings from Masked Autoencoders Are Scalable Vision Learners (MAE) on CIFAR-10: self-supervised pretraining improves downstream classification versus training from scratch, and we studied how decoder depth and decoder width affect MAE pretraining and downstream results.

Investigate possibilities for Vision Transformers with multiscale grids

MV-MAE is a hierarchical video model that leverages motion vectors and I-frames from compressed videos to efficiently learn masked motion representations for accurate UAV action recognition.

Implementing various to classify Noisy Birds

InfoMAE:Pair-Efficient Cross-Modal Alignment for Multimodal Time-Series Sensing