[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 BMVC2021 paper "Boundary Guided Context Aggregation for Semantic Segmentation"

Graph Self-Attention Network for Learning Spatial-Temporal Interaction Representation in Autonomous Driving

Code for Overinterpretation paper Overinterpretation reveals image classification model pathologies

This is an official implementation for "PlaneRecNet".

GPU-accelerated PyTorch implementation of Zero-shot User Intent Detection via Capsule Neural Networks

Group project for MFIN7036. Our goal is to predict firm profitability with text-based competition measures.

Implementation of the Swin Transformer in PyTorch.

Tensorflow 2.x implementation of Vision-Transformer model

code for Multi-scale Matching Networks for Semantic Correspondence, ICCV

Generic ecosystem for feature extraction from aerial and satellite imagery

FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection

This package implements the algorithms introduced in Smucler, Sapienza, and Rotnitzky (2020) to compute optimal adjustment sets in causal graphical models.

Official implementation of NLOS-OT: Passive Non-Line-of-Sight Imaging Using Optimal Transport (IEEE TIP, accepted)

Code to reproduce the results in the paper "Tensor Component Analysis for Interpreting the Latent Space of GANs".

scikit-learn inspired API for CRFsuite

(ICCV 2021) Official code of "Dressing in Order: Recurrent Person Image Generation for Pose Transfer, Virtual Try-on and Outfit Editing."

Text-to-Music Retrieval using Pre-defined/Data-driven Emotion Embeddings

Scripts for training an AI to play the endless runner Subway Surfers using a supervised machine learning approach by imitation and a convolutional neural network (CNN) for image classification

A python code to convert Keras pre-trained weights to Pytorch version

This is the implementation of GGHL (A General Gaussian Heatmap Labeling for Arbitrary-Oriented Object Detection)