[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

Recursive Bayesian Networks

TCTrack: Temporal Contexts for Aerial Tracking (CVPR2022)

Source code of SIGIR2021 Paper 'One Chatbot Per Person: Creating Personalized Chatbots based on Implicit Profiles'

Computing Shapley values using VAEAC

Implementation of "Scaled-YOLOv4: Scaling Cross Stage Partial Network" using PyTorch framwork.

Earthquake detection via fiber optic cables using deep learning

Understanding Convolutional Neural Networks from Theoretical Perspective via Volterra Convolution

Augmenting Physical Models with Deep Networks for Complex Dynamics Forecasting

my graduation project is about live human face augmentation by projection mapping by using CNN

[CVPR 2021] MiVOS - Mask Propagation module. Reproduced STM (and better) with training code :star2:. Semi-supervised video object segmentation evaluation.

Neural Turing Machine (NTM) & Differentiable Neural Computer (DNC) with pytorch & visdom

An open-source Kazakh named entity recognition dataset (KazNERD), annotation guidelines, and baseline NER models.

Torchreid: Deep learning person re-identification in PyTorch.

Codebase for testing whether hidden states of neural networks encode discrete structures.

A trashy useless Latin programming language written in python.

Whisper is a file-based time-series database format for Graphite.

Deep Learning for humans

CSPML (crystal structure prediction with machine learning-based element substitution)

Occlusion robust 3D face reconstruction model in CFR-GAN (WACV 2022)

Benchmarks for Object Detection in Aerial Images