PyTorch implementation of the Crafting Better Contrastive Views for Siamese Representation Learning

Last update: Dec 28, 2022

Related tags

Overview

Crafting Better Contrastive Views for Siamese Representation Learning

This is the official PyTorch implementation of the ContrastiveCrop paper:

@article{peng2022crafting,
  title={Crafting Better Contrastive Views for Siamese Representation Learning},
  author={Peng, Xiangyu and Wang, Kai and Zhu, Zheng and You, Yang},
  journal={arXiv preprint arXiv:2202.03278},
  year={2022}
}

This repo includes PyTorch implementation of SimCLR, MoCo, BYOL and SimSiam, as well as their DDP training code.

Preparation

Create a python enviroment with pytorch >= 1.8.1.
pip install -r requirements.txt
Modify dataset root in the config file.

Pre-train

# MoCo, CIFAR-10
python DDP_moco_ccrop.py configs/small/cifar10/moco_alpha0.1_th0.1.py

# SimSiam, CIFAR-100
python DDP_simsiam_ccrop.py configs/small/cifar100/simsiam_alpha0.1_th0.1.py

Linear Evaluation

# CIFAR-10
python DDP_linear.py configs/linear/cifar10_res18.py --load ./checkpoints/small/cifar10/moco_alpha0.1_th0.1/last.pth

# CIFAR-100
python DDP_linear.py configs/linear/cifar100_res18.py --load ./checkpoints/small/cifar100/simsiam_alpha0.1_th0.1/last.pth

More models and datasets coming soon.

PyTorch implementation of the Crafting Better Contrastive Views for Siamese Representation Learning

Related tags

Overview

Crafting Better Contrastive Views for Siamese Representation Learning

Preparation

Pre-train

Linear Evaluation

Owner

Code for Graph-to-Tree Learning for Solving Math Word Problems (ACL 2020)

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

All supplementary material used by me while TA-ing CS3244: Machine Learning

Using deep actor-critic model to learn best strategies in pair trading

Official PyTorch implementation of UACANet: Uncertainty Aware Context Attention for Polyp Segmentation

Pytorch implementation of DeePSiM

How Effective is Incongruity? Implications for Code-mix Sarcasm Detection.

Self-Supervised Vision Transformers Learn Visual Concepts in Histopathology (LMRL Workshop, NeurIPS 2021)

Spatially-Adaptive Pixelwise Networks for Fast Image Translation, CVPR 2021

Incremental Cross-Domain Adaptation for Robust Retinopathy Screening via Bayesian Deep Learning

Immortal tracker

Tgbox-bench - Simple TGBOX upload speed benchmark

Training DiffWave using variational method from Variational Diffusion Models.

A Novel Incremental Learning Driven Instance Segmentation Framework to Recognize Highly Cluttered Instances of the Contraband Items

DeFMO: Deblurring and Shape Recovery of Fast Moving Objects (CVPR 2021)

Spearmint Bayesian optimization codebase

Efficient Training of Audio Transformers with Patchout

NExT-QA: Next Phase of Question-Answering to Explaining Temporal Actions (CVPR2021)

👨‍💻 run nanosaur in simulation with Gazebo/Ingnition

Facial detection, landmark tracking and expression transfer library for Windows, Linux and Mac