[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

Code for "CloudAAE: Learning 6D Object Pose Regression with On-line Data Synthesis on Point Clouds" @ICRA2021

LiDAR Distillation: Bridging the Beam-Induced Domain Gap for 3D Object Detection

Deep functional residue identification

Learning Confidence for Out-of-Distribution Detection in Neural Networks

Semantic code search implementation using Tensorflow framework and the source code data from the CodeSearchNet project

Information-Theoretic Multi-Objective Bayesian Optimization with Continuous Approximations

VIL-100: A New Dataset and A Baseline Model for Video Instance Lane Detection (ICCV 2021)

Awesome Weak-Shot Learning

python library for invisible image watermark (blind image watermark)

This python-based package offers a way of creating a parametric OpenMC plasma source from plasma parameters.

[MedIA2021]MIDeepSeg: Minimally Interactive Segmentation of Unseen Objects from Medical Images Using Deep Learning

CNNs for Sentence Classification in PyTorch

VGGVox models for Speaker Identification and Verification trained on the VoxCeleb (1 & 2) datasets

Like ThreeJS but for Python and based on wgpu

RaftMLP: How Much Can Be Done Without Attention and with Less Spatial Locality?

Groceries ARL: Association Rules (Birliktelik Kuralı)

Geometry-Free View Synthesis: Transformers and no 3D Priors

PyTea: PyTorch Tensor shape error analyzer

Code + pre-trained models for the paper Keeping Your Eye on the Ball Trajectory Attention in Video Transformers

Koç University deep learning framework.