PyTorch implementation for COMPLETER: Incomplete Multi-view Clustering via Contrastive Prediction (CVPR 2021)

Related tags

Deep Learning clustering multi-view
Overview

Completer: Incomplete Multi-view Clustering via Contrastive Prediction

This repo contains the code and data of the following paper accepted by CVPR 2021

COMPLETER: Incomplete Multi-view Clustering via Contrastive Prediction

Requirements

pytorch==1.2.0

numpy>=1.19.1

scikit-learn>=0.23.2

munkres>=1.1.4

Configuration

The hyper-parameters, the training options (including the missing rate) are defined in configure.py.

Datasets

The Caltech101-20, LandUse-21, and Scene-15 datasets are placed in "data" folder. The NoisyMNIST dataset could be downloaded from cloud.

Usage

The code includes:

  • an example implementation of the model,
  • an example clustering task for different missing rates.
python run.py --dataset 0 --devices 0 --print_num 100 --test_time 5

You can get the following output:

Epoch : 100/500 ===> Reconstruction loss = 0.2819===> Reconstruction loss = 0.0320 ===> Dual prediction loss = 0.0199  ===> Contrastive loss = -4.4813e+02 ===> Loss = -4.4810e+02
view_concat {'kmeans': {'AMI': 0.5969, 'NMI': 0.6106, 'ARI': 0.6044, 'accuracy': 0.5813, 'precision': 0.4408, 'recall': 0.3835, 'f_measure': 0.3921}}
Epoch : 200/500 ===> Reconstruction loss = 0.2590===> Reconstruction loss = 0.0221 ===> Dual prediction loss = 0.0016  ===> Contrastive loss = -4.4987e+02 ===> Loss = -4.4984e+02
view_concat {'kmeans': {'AMI': 0.6575, 'NMI': 0.6691, 'ARI': 0.6974, 'accuracy': 0.6593, 'precision': 0.4551, 'recall': 0.4222, 'f_measure': 0.4096}}
Epoch : 300/500 ===> Reconstruction loss = 0.2450===> Reconstruction loss = 0.0207 ===> Dual prediction loss = 0.0011  ===> Contrastive loss = -4.5115e+02 ===> Loss = -4.5112e+02
view_concat {'kmeans': {'AMI': 0.6875, 'NMI': 0.6982, 'ARI': 0.8679, 'accuracy': 0.7439, 'precision': 0.4586, 'recall': 0.444, 'f_measure': 0.4217}}
Epoch : 400/500 ===> Reconstruction loss = 0.2391===> Reconstruction loss = 0.0210 ===> Dual prediction loss = 0.0007  ===> Contrastive loss = -4.5013e+02 ===> Loss = -4.5010e+02
view_concat {'kmeans': {'AMI': 0.692, 'NMI': 0.7027, 'ARI': 0.8736, 'accuracy': 0.7456, 'precision': 0.4601, 'recall': 0.4451, 'f_measure': 0.4257}}
Epoch : 500/500 ===> Reconstruction loss = 0.2281===> Reconstruction loss = 0.0187 ===> Dual prediction loss = 0.0008  ===> Contrastive loss = -4.5018e+02 ===> Loss = -4.5016e+02
view_concat {'kmeans': {'AMI': 0.6912, 'NMI': 0.7019, 'ARI': 0.8707, 'accuracy': 0.7464, 'precision': 0.4657, 'recall': 0.4464, 'f_measure': 0.4265}}

Citation

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

@inproceedings{lin2021completer,
   title={COMPLETER: Incomplete Multi-view Clustering via Contrastive Prediction},
   author={Lin, Yijie and Gou, Yuanbiao and Liu, Zitao and Li, Boyun and Lv, Jiancheng and Peng, Xi},
   booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
   month={June},
   year={2021}
}
You might also like...
Code for
Code for "Single-view robot pose and joint angle estimation via render & compare", CVPR 2021 (Oral).

Single-view robot pose and joint angle estimation via render & compare Yann Labbé, Justin Carpentier, Mathieu Aubry, Josef Sivic CVPR: Conference on C

Yann Labbé 51 Oct 14, 2022
git《FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding》(CVPR 2021) GitHub: [fig8]
git《FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding》(CVPR 2021) GitHub: [fig8]

FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding (CVPR 2021) This repo contains the implementation of our state-of-the-art fewshot ob

null 233 Dec 29, 2022
the code of the paper: Recurrent Multi-view Alignment Network for Unsupervised Surface Registration (CVPR 2021)
the code of the paper: Recurrent Multi-view Alignment Network for Unsupervised Surface Registration (CVPR 2021)

RMA-Net This repo is the implementation of the paper: Recurrent Multi-view Alignment Network for Unsupervised Surface Registration (CVPR 2021). Paper

Wanquan Feng 205 Nov 9, 2022
ESTDepth: Multi-view Depth Estimation using Epipolar Spatio-Temporal Networks (CVPR 2021)
ESTDepth: Multi-view Depth Estimation using Epipolar Spatio-Temporal Networks (CVPR 2021)

ESTDepth: Multi-view Depth Estimation using Epipolar Spatio-Temporal Networks (CVPR 2021) Project Page | Video | Paper | Data We present a novel metho

null 65 Nov 28, 2022
Continuous Query Decomposition for Complex Query Answering in Incomplete Knowledge Graphs

Continuous Query Decomposition This repository contains the official implementation for our ICLR 2021 (Oral) paper, Complex Query Answering with Neura

UCL Natural Language Processing 71 Dec 29, 2022
Incomplete easy-to-use math solver and PDF generator.

Math Expert Let me do your work Preview preview.mp4 Introduction Math Expert is our (@salastro, @younis-tarek, @marawn-mogeb) math high school graduat

SalahDin Ahmed 22 Jul 11, 2022
PyTorch implementation of paper
PyTorch implementation of paper "Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes", CVPR 2021

Neural Scene Flow Fields PyTorch implementation of paper "Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes", CVPR 20

Zhengqi Li 585 Jan 4, 2023
Re-implementation of the Noise Contrastive Estimation algorithm for pyTorch, following "Noise-contrastive estimation: A new estimation principle for unnormalized statistical models." (Gutmann and Hyvarinen, AISTATS 2010)

Noise Contrastive Estimation for pyTorch Overview This repository contains a re-implementation of the Noise Contrastive Estimation algorithm, implemen

Denis Emelin 42 Nov 24, 2022
VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning

This is a release of our VIMPAC paper to illustrate the implementations. The pretrained checkpoints and scripts will be soon open-sourced in HuggingFace transformers.

Hao Tan 74 Dec 3, 2022
Comments
  • about baseline AE2-Nets

    about baseline AE2-Nets

    AE2-Nets [1] is used as a baseline in the paper. But it seems that it's not originally designed for the incomplete scenario. Why can it be used as a baseline ? How is it adapted for such scenario ?

    1. Zhang C, Liu Y, Fu H. Ae2-nets: Autoencoder in autoencoder networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019: 2577-2585.
    opened by iTomxy 1
  • Require supplementary material

    Require supplementary material

    Dear author: Hello guys, great work! Could you kindly post your supplementary material. I can't find it in Prof Peng Xi's website. I want to see the detail presentation of Eq 6.

    With great thanks!

    opened by zheda-libin 1
  • Why is Gaussian distribution?

    Why is Gaussian distribution?

    Dear author, I don't quite understand one point. Is this representation Z discrete or continuous? If Z is discrete, why is the variational distribution Q simulated by Gaussian distribution instead of Bernoulli distribution?

    opened by kailugaji 2
Owner
XLearning Group
Xi Peng's XLearning Group
XLearning Group
GitHub
PyTorch implementation for Partially View-aligned Representation Learning with Noise-robust Contrastive Loss (CVPR 2021)

2021-CVPR-MvCLN This repo contains the code and data of the following paper accepted by CVPR 2021 Partially View-aligned Representation Learning with

XLearning Group 33 Nov 1, 2022
[CVPR'21] Projecting Your View Attentively: Monocular Road Scene Layout Estimation via Cross-view Transformation

Projecting Your View Attentively: Monocular Road Scene Layout Estimation via Cross-view Transformation Weixiang Yang, Qi Li, Wenxi Liu, Yuanlong Yu, Y

null 118 Dec 26, 2022
Pytorch implementation of Supporting Clustering with Contrastive Learning, NAACL 2021

Supporting Clustering with Contrastive Learning SCCL (NAACL 2021) Dejiao Zhang, Feng Nan, Xiaokai Wei, Shangwen Li, Henghui Zhu, Kathleen McKeown, Ram

null 231 Jan 5, 2023
PyTorch implementation of paper "IBRNet: Learning Multi-View Image-Based Rendering", CVPR 2021.

IBRNet: Learning Multi-View Image-Based Rendering PyTorch implementation of paper "IBRNet: Learning Multi-View Image-Based Rendering", CVPR 2021. IBRN

Google Interns 371 Jan 3, 2023
A PyTorch Implementation of "SINE: Scalable Incomplete Network Embedding" (ICDM 2018).

Scalable Incomplete Network Embedding ⠀⠀ A PyTorch implementation of Scalable Incomplete Network Embedding (ICDM 2018). Abstract Attributed network em

Benedek Rozemberczki 69 Sep 22, 2022
Blender add-on: Add to Cameras menu: View → Camera, View → Add Camera, Camera → View, Previous Camera, Next Camera

Blender add-on: Camera additions In 3D view, it adds these actions to the View|Cameras menu: View → Camera : set the current camera to the 3D view Vie

German Bauer 11 Feb 8, 2022
Collections for the lasted paper about multi-view clustering methods (papers, codes)

Multi-View Clustering Papers Collections for the lasted paper about multi-view clustering methods (papers, codes). There also exists some repositories

Andrew Guan 10 Sep 20, 2022
Graph Regularized Residual Subspace Clustering Network for hyperspectral image clustering

Graph Regularized Residual Subspace Clustering Network for hyperspectral image clustering

Yaoming Cai 5 Jul 18, 2022
Awesome Deep Graph Clustering is a collection of SOTA, novel deep graph clustering methods

ADGC: Awesome Deep Graph Clustering ADGC is a collection of state-of-the-art (SOTA), novel deep graph clustering methods (papers, codes and datasets).

yueliu1999 297 Dec 27, 2022
This is the code for the paper "Contrastive Clustering" (AAAI 2021)

Contrastive Clustering (CC) This is the code for the paper "Contrastive Clustering" (AAAI 2021) Dependency python>=3.7 pytorch>=1.6.0 torchvision>=0.8

Yunfan Li 210 Dec 30, 2022