[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

PyTorch implementation of 1712.06087 "Zero-Shot" Super-Resolution using Deep Internal Learning

Interactive dimensionality reduction for large datasets

nfelo: a power ranking, prediction, and betting model for the NFL

A Library for Modelling Probabilistic Hierarchical Graphical Models in PyTorch

Code for intrusion detection system (IDS) development using CNN models and transfer learning

Official code for our EMNLP2021 Outstanding Paper MindCraft: Theory of Mind Modeling for Situated Dialogue in Collaborative Tasks

An implementation of the research paper "Retina Blood Vessel Segmentation Using A U-Net Based Convolutional Neural Network"

Blind visual quality assessment on 360° Video based on progressive learning

Object Depth via Motion and Detection Dataset

This is the repository for our paper Ditch the Gold Standard: Re-evaluating Conversational Question Answering

This is the official source code of "BiCAT: Bi-Chronological Augmentation of Transformer for Sequential Recommendation".

Code release for the ICML 2021 paper "PixelTransformer: Sample Conditioned Signal Generation".

PyTorch implementation of spectral graph ConvNets, NIPS’16

Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Dark (ICCV 2021)

Official pytorch implementation of the paper: "SinGAN: Learning a Generative Model from a Single Natural Image"

This repository includes the official project for the paper: TransMix: Attend to Mix for Vision Transformers.

Pytorch implementation of SenFormer: Efficient Self-Ensemble Framework for Semantic Segmentation

This program was designed to detect whether someone is wearing a facemask through a live video stream.

Implementation of UNet on the Joey ML framework

Reference PyTorch implementation of "End-to-end optimized image compression with competition of prior distributions"