Official PyTorch Implementation of Convolutional Hough Matching Networks, CVPR 2021 (oral)

Last update: Nov 22, 2022

Related tags

Overview

Convolutional Hough Matching Networks

This is the implementation of the paper "Convolutional Hough Matching Network" by J. Min and M. Cho. Implemented on Python 3.7 and PyTorch 1.3.1.

For more information, check out project [website] and the paper on [arXiv]

Overall architecture:

Requirements

Python 3.7
PyTorch 1.3.1
cuda 10.1
pandas
requests

Conda environment settings:

conda create -n chm python=3.7
conda activate chm

conda install pytorch=1.3.1 torchvision cudatoolkit=10.1 -c pytorch
conda install -c anaconda requests
conda install -c conda-forge tensorflow
pip install tensorboardX
conda install -c anaconda pandas

Training

The code provides three types of CHM kernel: position-sensitive isotropic (psi), isotropic (iso), vanilla Nd (full).

python train.py --ktype {psi, iso, full} 
                --benchmark {spair, pfpascal}

Testing

Trained models are available on [Google drive].

python test.py --ktype {psi, iso, full} 
               --benchmark {spair, pfpascal, pfwillow} 
               --load 'path_to_trained_model'

For example, to reproduce our results in Table 1, refer following scripts.

python test.py --ktype psi --benchmark spair --load 'path_to_trained_model/spr_psi.pt'
python test.py --ktype psi --benchmark spair --load 'path_to_trained_model/pas_psi.pt'
python test.py --ktype psi --benchmark pfpascal --load 'path_to_trained_model/pas_psi.pt'
python test.py --ktype psi --benchmark pfwillow --load 'path_to_trained_model/pas_psi.pt'

BibTeX

If you use this code for your research, please consider citing:

@InProceedings{min2021chm, 
    author    = {Min, Juhong and Cho, Minsu},
    title     = {Convolutional Hough Matching Networks},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2021},
    pages     = {2940-2950}
}

Official PyTorch Implementation of Convolutional Hough Matching Networks, CVPR 2021 (oral)

Related tags

Overview

Convolutional Hough Matching Networks

Overall architecture:

Requirements

Training

Testing

BibTeX

Owner

Juhong Min

source code of Adversarial Feedback Loop Paper

Distributionally robust neural networks for group shifts

Learning to Initialize Neural Networks for Stable and Efficient Training

Official PyTorch implementation of "Physics-aware Difference Graph Networks for Sparsely-Observed Dynamics".

Autonomous Movement from Simultaneous Localization and Mapping

A simple python library for fast image generation of people who do not exist.

A repository for generating stylized talking 3D and 3D face

A naive ROS interface for visualDet3D.

The code for paper "Contrastive Spatio-Temporal Pretext Learning for Self-supervised Video Representation" which is accepted by AAAI 2022

A hobby project which includes a hand-gesture based virtual piano using a mobile phone camera and OpenCV library functions

an implementation of 3D Ken Burns Effect from a Single Image using PyTorch

CSE-519---Project - Job Title Analysis (Project for CSE 519 - Data Science Fundamentals)

Making Structure-from-Motion (COLMAP) more robust to symmetries and duplicated structures

code for our paper "Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer"

A machine learning benchmark of in-the-wild distribution shifts, with data loaders, evaluators, and default models.

Implementation of the Point Transformer layer, in Pytorch

Improving 3D Object Detection with Channel-wise Transformer

Classification of ecg datas for disease detection

一个多模态内容理解算法框架，其中包含数据处理、预训练模型、常见模型以及模型加速等模块。

XtremeDistil framework for distilling/compressing massive multilingual neural network models to tiny and efficient models for AI at scale