[CVPR 2022 Oral] Crafting Better Contrastive Views for Siamese Representation Learning

Last update: Dec 28, 2022

Overview

Crafting Better Contrastive Views for Siamese Representation Learning (CVPR 2022 Oral)

2022-03-29: The paper was selected as a CVPR 2022 Oral paper!

2022-03-03: The paper was accepted by CVPR 2022!

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, CCrop
python DDP_moco_ccrop.py configs/small/cifar10/moco_ccrop.py

# SimSiam, CIFAR-100, CCrop
python DDP_simsiam_ccrop.py configs/small/cifar100/simsiam_ccrop.py

# MoCo V2, IN-200, CCrop
python DDP_moco_ccrop.py configs/IN200/mocov2_ccrop.py

# MoCo V2, IN-1K, CCrop
python DDP_moco_ccrop.py configs/IN1K/mocov2_ccrop.py

We also recommend trying an even simpler version of ContrastiveCrop, named SimCCrop, that simply fixes a box at the center of the image with half height & width of that image. SimCCrop even does not require localization and thus adds NO extra training overhead. It should work well on almost 'object-centric' datasets.

# MoCo, SimCCrop
python DDP_moco_ccrop.py configs/small/cifar10/moco_simccrop.py
python DDP_moco_ccrop.py configs/small/cifar100/moco_simccrop.py

Linear Evaluation

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

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

# IN-200 
python DDP_linear.py configs/linear/IN200_res50.py --load ./checkpoints/IN200/mocov2_ccrop/last.pth

# IN-1K
python DDP_linear.py configs/linear/IN1K_res50.py --load ./checkpoints/IN1K/mocov2_ccrop/last.pth

More models and datasets coming soon.

[CVPR 2022 Oral] Crafting Better Contrastive Views for Siamese Representation Learning

Related tags

Overview

Crafting Better Contrastive Views for Siamese Representation Learning (CVPR 2022 Oral)

Preparation

Pre-train

Linear Evaluation

Owner

Learn about quantum computing and algorithm on quantum computing

Pretraining on Dynamic Graph Neural Networks

deep_image_prior_extension

Label Hallucination for Few-Shot Classification

pytorch implementation of dftd2 & dftd3

Codes for NAACL 2021 Paper "Unsupervised Multi-hop Question Answering by Question Generation"

Code for the CVPR2021 workshop paper "Noise Conditional Flow Model for Learning the Super-Resolution Space"

Public Code for NIPS submission SimiGrad: Fine-Grained Adaptive Batching for Large ScaleTraining using Gradient Similarity Measurement

Repo público onde postarei meus estudos de Python, buscando aprender por meio do compartilhamento do aprendizado!

Implementation of CoCa, Contrastive Captioners are Image-Text Foundation Models, in Pytorch

TCPNet - Temporal-attentive-Covariance-Pooling-Networks-for-Video-Recognition

Tools for computational pathology

ICCV2021 Papers with Code

An Ensemble of CNN (Python 3.5.1 Tensorflow 1.3 numpy 1.13)

This repository is the official implementation of Using Time-Series Privileged Information for Provably Efficient Learning of Prediction Models

Keywords : Streamlit, BertTokenizer, BertForMaskedLM, Pytorch

Totally Versatile Miscellanea for Pytorch

[CVPR 2022] TransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial Editing

The fastai book, published as Jupyter Notebooks

Code for Max-Margin Contrastive Learning - AAAI 2022