PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations

solo-learn: a library of self-supervised methods for visual representation learning powered by Pytorch Lightning

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

SOTA Semantic Segmentation Models in PyTorch

PyTorch code for "Prototypical Contrastive Learning of Unsupervised Representations"

Benchmark your model on out-of-distribution datasets with carefully collected human comparison data (NeurIPS 2021 Oral)

Unofficial pytorch implementation of 'Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization' [Huang+, ICCV2017]

PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722

GPU Accelerated t-SNE for CUDA with Python bindings

TRACER: Extreme Attention Guided Salient Object Tracing Network (AAAI 2022) implementation in PyTorch

SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners

Pre-trained models, data, code & materials from the paper "ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness" (ICLR 2019 Oral)

Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"

[CVPRW'22] Unsupervised Salient Object Detection With Spectral Cluster Voting

PyTorch implementation of SwAV https//arxiv.org/abs/2006.09882

Full-gradient saliency maps

PyTorch implementation of SimSiam https//arxiv.org/abs/2011.10566

Code for MOVE: Unsupervised Movable Object Segmentation and Detection; NeurIPS 2022

A package for decomposing multi-channel EMG signals into individual motor unit activity.

PyTorch implementation of Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning

PyTorch implementation of Barlow Twins.

Code to train CLIP model

PyTorch implementation of MoCo v3 https//arxiv.org/abs/2104.02057

This repository is an implementation for the loss function proposed in https://arxiv.org/pdf/2110.06848.pdf.

Poisson Identifiable VAE (pi-VAE)

Monocular depth estimation by segmentation models for NYU-depth v2 dataset. Simple PyTorch Lightning implementation.