[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

Moon-patrol - A faithful recreation of the 1983 hit classic Moon Patrol for the Atari 2600 created using the Pygame library for Python

An MQA (Studio, originalSampleRate) identifier for lossless flac files written in Python.

Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework

NU-Wave: A Diffusion Probabilistic Model for Neural Audio Upsampling

Simple and ready-to-use tutorials for TensorFlow

Per-Pixel Classification is Not All You Need for Semantic Segmentation

FedMM: Saddle Point Optimization for Federated Adversarial Domain Adaptation

基于PaddleClas实现垃圾分类，并转换为inference格式用PaddleHub服务端部署

MAME is a multi-purpose emulation framework.

Code for the paper "SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness" (NeurIPS 2021)

🧑‍🔬 verify your TEAL program by experiment and observation

Joint parameterization and fitting of stroke clusters

Deep learning for Engineers - Physics Informed Deep Learning

Explaining Deep Neural Networks - A comparison of different CAM methods based on an insect data set

[ICCV 2021] Relaxed Transformer Decoders for Direct Action Proposal Generation

[CVPR 2022] Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels

Sound and Cost-effective Fuzzing of Stripped Binaries by Incremental and Stochastic Rewriting

PyTorch implementation HoroPCA: Hyperbolic Dimensionality Reduction via Horospherical Projections

Civsim is a basic civilisation simulation and modelling system built in Python 3.8.

Parasite: a tool allowing you to compress and decompress files, to reduce their size