Code of our paper "Contrastive Object-level Pre-training with Spatial Noise Curriculum Learning"

Last update: Dec 13, 2022

Related tags

Deep Learning CCOP

Overview

CCOP

Code of our paper Contrastive Object-level Pre-training with Spatial Noise Curriculum Learning

Requirement

Install OpenSelfSup
Install Detectron2, Do not forget to setup Detectron2 datasets!!!
Install Kornia for fast data augmentation

Usage

Run Selective Search

% remember to setup the dataset paths
python tools/selective_search.py

Setup dataset

mkdir data
ln -s path_to_coco data

Run CCOP pre-training and Mask R-CNN benchmark

% training a ResNet-50 model with 8 GPU
zsh tools/det_train_benchmark.sh configs/selfsup/ccop/r50_d2.py 8 path_to_output

Citation

@article{yang2021contrastive,
  title={Contrastive Object-level Pre-training with Spatial Noise Curriculum Learning},
  author={Yang, Chenhongyi and Huang, Lichao and Crowley, Elliot J},
  journal={arXiv preprint arXiv:2111.13651},
  year={2021}
}

Owner

Chenhongyi Yang

Ph.D. student at the University of Edinburgh.

GitHub Repository

A new test set for ImageNet

ImageNetV2 The ImageNetV2 dataset contains new test data for the ImageNet benchmark. This repository provides associated code for assembling and worki

186 Dec 18, 2022

PyTorch Code for "Generalization in Dexterous Manipulation via Geometry-Aware Multi-Task Learning"

Generalization in Dexterous Manipulation via Geometry-Aware Multi-Task Learning [Project Page] [Paper] Wenlong Huang1, Igor Mordatch2, Pieter Abbeel1,

40 Nov 22, 2022

Any-to-any voice conversion using synthetic specific-speaker speeches as intermedium features

MediumVC MediumVC is an utterance-level method towards any-to-any VC. Before that, we propose SingleVC to perform A2O tasks(Xi → Ŷi) , Xi means utter

47 Dec 25, 2022

PyTorch implementation of deep GRAph Contrastive rEpresentation learning (GRACE).

GRACE The official PyTorch implementation of deep GRAph Contrastive rEpresentation learning (GRACE). For a thorough resource collection of self-superv

186 Dec 27, 2022

Efficient Training of Visual Transformers with Small Datasets

Official codes for "Efficient Training of Visual Transformers with Small Datasets", NerIPS 2021.

112 Dec 25, 2022

nnDetection is a self-configuring framework for 3D (volumetric) medical object detection which can be applied to new data sets without manual intervention. It includes guides for 12 data sets that were used to develop and evaluate the performance of the proposed method.

What is nnDetection? Simultaneous localisation and categorization of objects in medical images, also referred to as medical object detection, is of hi

365 Jan 09, 2023

Official codebase for Pretrained Transformers as Universal Computation Engines.

universal-computation Overview Official codebase for Pretrained Transformers as Universal Computation Engines. Contains demo notebook and scripts to r

210 Dec 28, 2022

Pytorch and Torch testing code of CartoonGAN

CartoonGAN-Test-Pytorch-Torch Pytorch and Torch testing code of CartoonGAN [Chen et al., CVPR18]. With the released pretrained models by the authors,

642 Dec 27, 2022

Where2Act: From Pixels to Actions for Articulated 3D Objects

Where2Act: From Pixels to Actions for Articulated 3D Objects The Proposed Where2Act Task. Given as input an articulated 3D object, we learn to propose

69 Nov 28, 2022

Non-Official Pytorch implementation of "Face Identity Disentanglement via Latent Space Mapping" https://arxiv.org/abs/2005.07728 Using StyleGAN2 instead of StyleGAN

Face Identity Disentanglement via Latent Space Mapping - Implement in pytorch with StyleGAN 2 Description Pytorch implementation of the paper Face Ide

58 Dec 24, 2022

Unofficial pytorch implementation of the paper "Dynamic High-Pass Filtering and Multi-Spectral Attention for Image Super-Resolution"

DFSA Unofficial pytorch implementation of the ICCV 2021 paper "Dynamic High-Pass Filtering and Multi-Spectral Attention for Image Super-Resolution" (p

2 Nov 15, 2021