[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

[ArXiv 2021] Data-Efficient Instance Generation from Instance Discrimination

ObjectDrawer-ToolBox: a graphical image annotation tool to generate ground plane masks for a 3D object reconstruction system

Re-implementation of 'Grokking: Generalization beyond overfitting on small algorithmic datasets'

Multi-Agent Reinforcement Learning (MARL) method to learn scalable control polices for multi-agent target tracking.

GAN JAX - A toy project to generate images from GANs with JAX

CLIP2Video: Mastering Video-Text Retrieval via Image CLIP

Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021

Proof of concept GnuCash Webinterface

How Do Adam and Training Strategies Help BNNs Optimization? In ICML 2021.

Breaking the Dilemma of Medical Image-to-image Translation

Large-scale Hyperspectral Image Clustering Using Contrastive Learning, CIKM 21 Workshop

PassAPI is a password generator in hash format and fully developed in Python, with the aim of teaching how to handle and build

MoCoGAN: Decomposing Motion and Content for Video Generation

[NeurIPS'21 Spotlight] PyTorch code for our paper "Aligned Structured Sparsity Learning for Efficient Image Super-Resolution"

Generating Digital Painting Lighting Effects via RGB-space Geometry (SIGGRAPH2020/TOG2020)

An implementation of the "Attention is all you need" paper without extra bells and whistles, or difficult syntax

Fine-grained Post-training for Improving Retrieval-based Dialogue Systems - NAACL 2021

내가 보려고 정리한 <프로그래밍 기초 Ⅰ> / organized for me

Populating 3D Scenes by Learning Human-Scene Interaction https://posa.is.tue.mpg.de/

Codes for TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization.