[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

Complementary Patch for Weakly Supervised Semantic Segmentation, ICCV21 (poster)

A PyTorch Toolbox for Face Recognition

A CROSS-MODAL FUSION NETWORK BASED ON SELF-ATTENTION AND RESIDUAL STRUCTURE FOR MULTIMODAL EMOTION RECOGNITION

Code release for Universal Domain Adaptation(CVPR 2019)

Code for the paper "Unsupervised Contrastive Learning of Sound Event Representations", ICASSP 2021.

Nested Graph Neural Network (NGNN) is a general framework to improve a base GNN's expressive power and performance

Keqing Chatbot With Python

Temporally Efficient Vision Transformer for Video Instance Segmentation, CVPR 2022, Oral

Fast and robust clustering of point clouds generated with a Velodyne sensor.

PyTorch implementation of PNASNet-5 on ImageNet

Localized representation learning from Vision and Text (LoVT)

Semi-Supervised Learning, Object Detection, ICCV2021

Codes for the paper Contrast and Mix: Temporal Contrastive Video Domain Adaptation with Background Mixing

Random Walk Graph Neural Networks

The codes and models in 'Gaze Estimation using Transformer'.

Official Implementation of Neural Splines

[CVPR 2021] NormalFusion: Real-Time Acquisition of Surface Normals for High-Resolution RGB-D Scanning

Repository for code and dataset for our EMNLP 2021 paper - “So You Think You’re Funny?”: Rating the Humour Quotient in Standup Comedy.

A PyTorch implementation of "Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks" (KDD 2019).

Implementation for Shape from Polarization for Complex Scenes in the Wild