[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

Unrolled Generative Adversarial Networks

Inferred Model-based Fuzzer

DNA-RECON { Automatic Web Reconnaissance Tool }

Swin-Transformer is basically a hierarchical Transformer whose representation is computed with shifted windows.

ISNAS-DIP: Image Specific Neural Architecture Search for Deep Image Prior [CVPR 2022]

This is an official implementation for "Video Swin Transformers".

LERP : Label-dependent and event-guided interpretable disease risk prediction using EHRs

Code for Graph-to-Tree Learning for Solving Math Word Problems (ACL 2020)

The official implementation of A Unified Game-Theoretic Interpretation of Adversarial Robustness.

Pre-Training 3D Point Cloud Transformers with Masked Point Modeling

A series of convenience functions to make basic image processing operations such as translation, rotation, resizing, skeletonization, and displaying Matplotlib images easier with OpenCV and Python.

offical implement of our Lifelong Person Re-Identification via Adaptive Knowledge Accumulation in CVPR2021

Omnidirectional Scene Text Detection with Sequential-free Box Discretization (IJCAI 2019). Including competition model, online demo, etc.

Run containerized, rootless applications with podman

HyperLib: Deep learning in the Hyperbolic space

My personal Home Assistant configuration.

python debugger and anti-vm that checks if you're in a virtual machine or if someones trying to debug your file

Code for "The Box Size Confidence Bias Harms Your Object Detector"

DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.

Learning Correspondence from the Cycle-consistency of Time (CVPR 2019)