[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

Implementation of the Swin Transformer in PyTorch.

The offcial repository for 'CharacterBERT and Self-Teaching for Improving the Robustness of Dense Retrievers on Queries with Typos', SIGIR2022

PyTorch implementation of the ExORL: Exploratory Data for Offline Reinforcement Learning

Code for the paper "On the Power of Edge Independent Graph Models"

Attention-based CNN-LSTM and XGBoost hybrid model for stock prediction

CLOCs: Camera-LiDAR Object Candidates Fusion for 3D Object Detection

Bootstrapped Unsupervised Sentence Representation Learning (ACL 2021)

TransGAN: Two Transformers Can Make One Strong GAN

Generative Query Network (GQN) in PyTorch as described in "Neural Scene Representation and Rendering"

Some experiments with tennis player aging curves using Hilbert space GPs in PyMC. Only experimental for now.

A Large-Scale Dataset for Spinal Vertebrae Segmentation in Computed Tomography

Python project to take sound as input and output as RGB + Brightness values suitable for DMX

A script depending on VASP output for calculating Fermi-Softness.

Graph Representation Learning via Graphical Mutual Information Maximization

Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labels

Human Pose estimation with TensorFlow framework

Biomarker identification for COVID-19 Severity in BALF cells Single-cell RNA-seq data

FishNet: One Stage to Detect, Segmentation and Pose Estimation

SatelliteNeRF - PyTorch-based Neural Radiance Fields adapted to satellite domain

Codes for Causal Semantic Generative model (CSG), the model proposed in "Learning Causal Semantic Representation for Out-of-Distribution Prediction" (NeurIPS-21)