PyTorch implementation of Contrastive Learning methods
A simple to use pytorch wrapper for contrastive self-supervised learning on any neural network
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722
[ECCV 2020] "Contrastive Multiview Coding", also contains implementations for MoCo and InstDis
PyTorch implementation of DeepMind's DetCon from "Efficient Visual Pretraining with Contrastive D...
PyTorch code for CVPR 2018 paper: Learning to Compare: Relation Network for Few-Shot Learning (Fe...
Object Detection and Multi-Object Tracking
Pytorch Implementation for CVPR2018 Paper: Learning to Compare: Relation Network for Few-Shot Lea...
Implementation of COCO-LM, Correcting and Contrasting Text Sequences for Language Model Pretraini...
PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)
Usable Implementation of "Bootstrap Your Own Latent" self-supervised learning, from Deepmind, in ...
Sequence modeling benchmarks and temporal convolutional networks
I decide to sync up this repo and self-critical.pytorch. (The old master is in old master branch ...
Implementation of Pixel-level Contrastive Learning, proposed in the paper "Propagate Yourself", i...
Dense Contrastive Learning (DenseCL) for self-supervised representation learning, CVPR 2021 Oral.