[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

you can add any codes in any language by creating its respective folder (if already not available).

FLSim a flexible, standalone library written in PyTorch that simulates FL settings with a minimal, easy-to-use API

ViewFormer: NeRF-free Neural Rendering from Few Images Using Transformers

Checking fibonacci - Generating the Fibonacci sequence is a classic recursive problem

Towards Implicit Text-Guided 3D Shape Generation (CVPR2022)

SMD-Nets: Stereo Mixture Density Networks

[ICCV' 21] "Unsupervised Point Cloud Pre-training via Occlusion Completion"

Code release for ICCV 2021 paper "Anticipative Video Transformer"

Code for Discriminative Sounding Objects Localization (NeurIPS 2020)

Binary classification for arrythmia detection with ECG datasets.

Tutorial page of the Climate Hack, the greatest hackathon ever

This is the official implementation for "Do Transformers Really Perform Bad for Graph Representation?".

Simulation of moving particles under microscopic imaging

[ICML 2020] DrRepair: Learning to Repair Programs from Error Messages

2021 National Underwater Robotics Vision Optics

A very impractical 3D rendering engine that runs in the python terminal.

Square Root Bundle Adjustment for Large-Scale Reconstruction

[CVPR 2021] Forecasting the panoptic segmentation of future video frames

SkipGNN: Predicting Molecular Interactions with Skip-Graph Networks (Scientific Reports)

A certifiable defense against adversarial examples by training neural networks to be provably robust