Self Supervised Learning

lightly - A computer vision framework for self-supervised learningPython

A Python library for self-supervised learning on images, providing a modular PyTorch-like framework with support for modern SSL models.

SfMLearnerJupyter Notebook

An unsupervised learning framework for depth and ego-motion estimation from monocular videos using TensorFlow.

ProtTransJupyter Notebook

State-of-the-art pre-trained transformer language models for protein sequences, enabling tasks like structure prediction and function annotation.

packnet-sfmPython

A PyTorch implementation of self-supervised monocular depth estimation using 3D packing for high-resolution, real-time depth prediction.

OpenMetricLearningPython

A PyTorch-based framework for training and validating models that produce high-quality embeddings for metric learning and retrieval tasks.

PASS: An An ImageNet replacement for self-supervised pretraining without humansPython

A large-scale image dataset for self-supervised pretraining without humans, designed to reduce privacy concerns.

CalibnetPython

A self-supervised deep learning model for extrinsic calibration between LiDAR and camera sensors using 3D spatial transformer networks.