[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

Official implementation of "UCTransNet: Rethinking the Skip Connections in U-Net from a Channel-wise Perspective with Transformer"

An experiment on the performance of homemade Q-learning AIs in Agar.io depending on their state representation and available actions

[ICCV'2021] "SSH: A Self-Supervised Framework for Image Harmonization", Yifan Jiang, He Zhang, Jianming Zhang, Yilin Wang, Zhe Lin, Kalyan Sunkavalli, Simon Chen, Sohrab Amirghodsi, Sarah Kong, Zhangyang Wang

Trading Gym is an open source project for the development of reinforcement learning algorithms in the context of trading.

STRIVE: Scene Text Replacement In Videos

Deep Illuminator is a data augmentation tool designed for image relighting. It can be used to easily and efficiently generate a wide range of illumination variants of a single image.

An implementation of chunked, compressed, N-dimensional arrays for Python.

Efficient Two-Step Networks for Temporal Action Segmentation (Neurocomputing 2021)

We provided a matlab implementation for an evolutionary multitasking AUC optimization framework (EMTAUC).

Public Code for NIPS submission SimiGrad: Fine-Grained Adaptive Batching for Large ScaleTraining using Gradient Similarity Measurement

Torchreid: Deep learning person re-identification in PyTorch.

UniFormer - official implementation of UniFormer

PyTorch code for 'Efficient Single Image Super-Resolution Using Dual Path Connections with Multiple Scale Learning'

Official PyTorch implementation of "VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization" (CVPR 2021)

pq is a jq-like Pickle file viewer

Style-based Neural Drum Synthesis with GAN inversion

Official Implementation of 'UPDeT: Universal Multi-agent Reinforcement Learning via Policy Decoupling with Transformers' ICLR 2021(spotlight)

PyTorch implementation of Soft-DTW: a Differentiable Loss Function for Time-Series in CUDA

This is the code of "Multi-view Contrastive Graph Clustering" in NeurlPS 2021.

A facial recognition doorbell system using a Raspberry Pi