[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

Locally cache assets that are normally streamed in POPULATION: ONE

Code for the ICCV 2021 paper "Pixel Difference Networks for Efficient Edge Detection" (Oral).

Global Pooling, More than Meets the Eye: Position Information is Encoded Channel-Wise in CNNs, ICCV 2021

BEAMetrics: Benchmark to Evaluate Automatic Metrics in Natural Language Generation

Everything you need to know about NumPy( Creating Arrays, Indexing, Math,Statistics,Reshaping).

Bonnet: An Open-Source Training and Deployment Framework for Semantic Segmentation in Robotics.

ICRA 2021 "Towards Precise and Efficient Image Guided Depth Completion"

DeepConsensus uses gap-aware sequence transformers to correct errors in Pacific Biosciences (PacBio) Circular Consensus Sequencing (CCS) data.

MaskTrackRCNN for video instance segmentation based on mmdetection

Official implementation of "Learning Not to Reconstruct" (BMVC 2021)

A wrapper around SageMaker ML Lineage Tracking extending ML Lineage to end-to-end ML lifecycles, including additional capabilities around Feature Store groups, queries, and other relevant artifacts.

This is a yolo3 implemented via tensorflow 2.7

Generative Modelling of BRDF Textures from Flash Images [SIGGRAPH Asia, 2021]

Implementation of Bidirectional Recurrent Independent Mechanisms (Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules)

Calibrated Hyperspectral Image Reconstruction via Graph-based Self-Tuning Network.

Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Clouds (CVPR 2022)

A simple software for capturing human body movements using the Kinect camera.

EfficientNetV2-with-TPU - Cifar-10 case study

Python Multi-Agent Reinforcement Learning framework

S2s2net - Sentinel-2 Super-Resolution Segmentation Network