This project is the official implementation of our accepted ICLR 2021 paper BiPointNet: Binary Neural Network for Point Clouds.

Overview

BiPointNet: Binary Neural Network for Point Clouds

Created by Haotong Qin, Zhongang Cai, Mingyuan Zhang, Yifu Ding, Haiyu Zhao, Shuai Yi, Xianglong Liu, and Hao Su from Beihang University, SenseTime, and UCSD.

prediction example

Introduction

This project is the official implementation of our accepted ICLR 2021 paper BiPointNet: Binary Neural Network for Point Clouds [PDF]. To alleviate the resource constraint for real-time point cloud applications that run on edge devices, in this paper we present BiPointNet, the first model binarization approach for efficient deep learning on point clouds. We first discover that the immense performance drop of binarized models for point clouds mainly stems from two challenges: aggregation-induced feature homogenization that leads to a degradation of information entropy, and scale distortion that hinders optimization and invalidates scale-sensitive structures. With theoretical justifications and in-depth analysis, our BiPointNet introduces Entropy-Maximizing Aggregation (EMA) to modulate the distribution before aggregation for the maximum information entropy, and Layer-wise Scale Recovery (LSR) to efficiently restore feature representation capacity. Extensive experiments show that BiPointNet outperforms existing binarization methods by convincing margins, at the level even comparable with the full precision counterpart. We highlight that our techniques are generic, guaranteeing significant improvements on various fundamental tasks and mainstream backbones, e.g., BiPointNet gives an impressive 14.7x speedup and 18.9x storage saving on real-world resource-constrained devices.

Installation

# create new conda environment
conda create -n pyg python=3.7 -y
conda activate pyg

# install pytorch
conda install pytorch==1.5.0 torchvision cudatoolkit=10.1 -c pytorch -y

# install pytorch-geometric
export CUDA=cu101
pip install torch-scatter==latest+${CUDA} -f https://pytorch-geometric.com/whl/torch-1.5.0.html
pip install torch-sparse==latest+${CUDA} -f https://pytorch-geometric.com/whl/torch-1.5.0.html
pip install torch-cluster==latest+${CUDA} -f https://pytorch-geometric.com/whl/torch-1.5.0.html
pip install torch-spline-conv==latest+${CUDA} -f https://pytorch-geometric.com/whl/torch-1.5.0.html
pip install torch-geometric

# install other dependencies
pip install pyyaml

Training

export PYTHONPATH=$(pwd):$PYTHONPATH
conda activate pyg
python scripts/main.py ${CONFIG} ${PYTHON_ARGS}

Citation

If you find our work useful in your research, please consider citing:

@inproceedings{Qin:iclr21,
  author    = {Haotong Qin and Zhongang Cai and Mingyuan Zhang 
  and Yifu Ding and Haiyu Zhao and Shuai Yi 
  and Xianglong Liu and Hao Su},
  title     = {BiPointNet: Binary Neural Network for Point Clouds},
  booktitle = {ICLR},
  year      = {2021}
}
You might also like...
(CVPR 2022 Oral) Official implementation for
(CVPR 2022 Oral) Official implementation for "Surface Representation for Point Clouds"

RepSurf - Surface Representation for Point Clouds [CVPR 2022 Oral] By Haoxi Ran* , Jun Liu, Chengjie Wang ( * : corresponding contact) The pytorch off

Code for the paper "Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds" (ICCV 2021)

Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds This is the official code implementation for the paper "Spatio-temporal Se

Code for the paper SphereRPN: Learning Spheres for High-Quality Region Proposals on 3D Point Clouds Object Detection, ICIP 2021.

SphereRPN Code for the paper SphereRPN: Learning Spheres for High-Quality Region Proposals on 3D Point Clouds Object Detection, ICIP 2021. Authors: Th

Public repository of the 3DV 2021 paper "Generative Zero-Shot Learning for Semantic Segmentation of 3D Point Clouds"

Generative Zero-Shot Learning for Semantic Segmentation of 3D Point Clouds Björn Michele1), Alexandre Boulch1), Gilles Puy1), Maxime Bucher1) and Rena

This repo is a PyTorch implementation for Paper
This repo is a PyTorch implementation for Paper "Unsupervised Learning for Cuboid Shape Abstraction via Joint Segmentation from Point Clouds"

Unsupervised Learning for Cuboid Shape Abstraction via Joint Segmentation from Point Clouds This repository is a PyTorch implementation for paper: Uns

Unofficial implementation of Point-Unet: A Context-Aware Point-Based Neural Network for Volumetric Segmentation

Point-Unet This is an unofficial implementation of the MICCAI 2021 paper Point-Unet: A Context-Aware Point-Based Neural Network for Volumetric Segment

An implementation demo of the ICLR 2021 paper Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks in PyTorch.

Neural Attention Distillation This is an implementation demo of the ICLR 2021 paper Neural Attention Distillation: Erasing Backdoor Triggers from Deep

《A-CNN: Annularly Convolutional Neural Networks on Point Clouds》(2019)
《A-CNN: Annularly Convolutional Neural Networks on Point Clouds》(2019)

A-CNN: Annularly Convolutional Neural Networks on Point Clouds Created by Artem Komarichev, Zichun Zhong, Jing Hua from Department of Computer Science

(CVPR 2021) PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds
(CVPR 2021) PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds

PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds by Mutian Xu*, Runyu Ding*, Hengshuang Zhao, and Xiaojuan Qi. Int

Comments
  • TypeError

    TypeError

    I met the following error while running the code:

    Traceback (most recent call last): File "C:/Users/Admin/Documents/code/BiPointNet/scripts/main.py", line 31, in cfg, stem = parse_cfg(args.cfg) File "C:\Users\Admin\Documents\code\BiPointNet\utils\utils.py", line 96, in parse_cfg with open(path, 'r') as f: TypeError: expected str, bytes or os.PathLike object, not NoneType

    May I ask which file path is imported by the ‘cfg’ parameter? Looking forward to your reply, thanks!

    opened by ldk-97 0
  • About the steps of training

    About the steps of training

    Thank you very much for your contribution. In this contribution, I did not find a complete training process, such as which data set to use, training steps, etc. I would appreciate it if you can add further

    opened by 123zhen123 0
Owner
Haotong Qin
PhD Student in CS @ Beihang University (BUAA) @ SKLSDE Lab. #DeepLearning #ModelCompression #Quantization #ComputerVision
Haotong Qin
Code for "PV-RAFT: Point-Voxel Correlation Fields for Scene Flow Estimation of Point Clouds", CVPR 2021

PV-RAFT This repository contains the PyTorch implementation for paper "PV-RAFT: Point-Voxel Correlation Fields for Scene Flow Estimation of Point Clou

Yi Wei 43 Dec 5, 2022
The official implementation of ICCV paper "Box-Aware Feature Enhancement for Single Object Tracking on Point Clouds".

Box-Aware Tracker (BAT) Pytorch-Lightning implementation of the Box-Aware Tracker. Box-Aware Feature Enhancement for Single Object Tracking on Point C

Kangel Zenn 5 Mar 26, 2022
A Research-oriented Federated Learning Library and Benchmark Platform for Graph Neural Networks. Accepted to ICLR'2021 - DPML and MLSys'21 - GNNSys workshops.

FedGraphNN: A Federated Learning System and Benchmark for Graph Neural Networks A Research-oriented Federated Learning Library and Benchmark Platform

FedML-AI 175 Dec 1, 2022
Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds (CVPR 2022, Oral)

Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds (CVPR 2022, Oral) This is the official implementat

Yifan Zhang 259 Dec 25, 2022
Implementation of Geometric Vector Perceptron, a simple circuit for 3d rotation equivariance for learning over large biomolecules, in Pytorch. Idea proposed and accepted at ICLR 2021

Geometric Vector Perceptron Implementation of Geometric Vector Perceptron, a simple circuit with 3d rotation equivariance for learning over large biom

Phil Wang 59 Nov 24, 2022
This repo contains the pytorch implementation for Dynamic Concept Learner (accepted by ICLR 2021).

DCL-PyTorch Pytorch implementation for the Dynamic Concept Learner (DCL). More details can be found at the project page. Framework Grounding Physical

Zhenfang Chen 31 Jan 6, 2023
Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces(ICML 2021)

Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces(ICML 2021) This repository contains the code

null 149 Dec 15, 2022
Official PyTorch implementation of the preprint paper "Stylized Neural Painting", accepted to CVPR 2021.

Official PyTorch implementation of the preprint paper "Stylized Neural Painting", accepted to CVPR 2021.

Zhengxia Zou 1.5k Dec 28, 2022
This is the code repository implementing the paper "TreePartNet: Neural Decomposition of Point Clouds for 3D Tree Reconstruction".

TreePartNet This is the code repository implementing the paper "TreePartNet: Neural Decomposition of Point Clouds for 3D Tree Reconstruction". Depende

刘彦超 34 Nov 30, 2022
Official PyTorch implementation of CAPTRA: CAtegory-level Pose Tracking for Rigid and Articulated Objects from Point Clouds

CAPTRA: CAtegory-level Pose Tracking for Rigid and Articulated Objects from Point Clouds Introduction This is the official PyTorch implementation of o

Yijia Weng 96 Dec 7, 2022