[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

Differentiable Surface Triangulation

A simple python library for fast image generation of people who do not exist.

code for `Look Closer to Segment Better: Boundary Patch Refinement for Instance Segmentation`

TensorFlow Tutorial and Examples for Beginners (support TF v1 & v2)

PyElastica is the Python implementation of Elastica, an open-source software for the simulation of assemblies of slender, one-dimensional structures using Cosserat Rod theory.

ColossalAI-Benchmark - Performance benchmarking with ColossalAI

🌈 PyTorch Implementation for EMNLP'21 Findings "Reasoning Visual Dialog with Sparse Graph Learning and Knowledge Transfer"

RepVGG: Making VGG-style ConvNets Great Again

A python software that can help blind people find things like laptops, phones, etc the same way a guide dog guides a blind person in finding his way.

This project helps to colorize grayscale images using multiple exemplars.

GPT, but made only out of gMLPs

OpenMatch: Open-set Consistency Regularization for Semi-supervised Learning with Outliers (NeurIPS 2021)

Introducing neural networks to predict stock prices

RuDOLPH: One Hyper-Modal Transformer can be creative as DALL-E and smart as CLIP

This is the official implementation for the paper "Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and Generalization" in NeurIPS 2021.

InDuDoNet+: A Model-Driven Interpretable Dual Domain Network for Metal Artifact Reduction in CT Images

✂️ EyeLipCropper is a Python tool to crop eyes and mouth ROIs of the given video.

A transformer model to predict pathogenic mutations

Code release for General Greedy De-bias Learning

Certified Patch Robustness via Smoothed Vision Transformers