[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

This repository contains the segmentation user interface from the OpenSurfaces project, extracted as a lightweight tool

pytorch implementation of fast-neural-style

Benchmarking the robustness of Spatial-Temporal Models

[CVPR 2022] PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision (Oral)

Collection of tasks for fast prototyping, baselining, finetuning and solving problems with deep learning.

LoL Runes Recommender With Python

Source code for PairNorm (ICLR 2020)

This Jupyter notebook shows one way to implement a simple first-order low-pass filter on sampled data in discrete time.

HistoSeg : Quick attention with multi-loss function for multi-structure segmentation in digital histology images

A PyTorch implementation of DenseNet.

A lightweight python AUTOmatic-arRAY library.

[AI6122] Text Data Management & Processing

Official Python implementation of the 'Sparse deconvolution'-v0.3.0

Implementation of H-Transformer-1D, Hierarchical Attention for Sequence Learning using 🤗 transformers

Poplar implementation of "Bundle Adjustment on a Graph Processor" (CVPR 2020)

Tensorflow implementation of Human-Level Control through Deep Reinforcement Learning

Vision Transformer for 3D medical image registration (Pytorch).

QAT(quantize aware training) for classification with MQBench

Emulation and Feedback Fuzzing of Firmware with Memory Sanitization

The code for our paper submitted to RAL/IROS 2022: OverlapTransformer: An Efficient and Rotation-Invariant Transformer Network for LiDAR-Based Place Recognition.