TraND: Transferable Neighborhood Discovery for Unsupervised Cross-domain Gait Recognition.

Last update: Apr 04, 2022

Overview

TraND

This is the code for the paper "Jinkai Zheng, Xinchen Liu, Chenggang Yan, Jiyong Zhang, Wu Liu, Xiaoping Zhang and Tao Mei: TraND: Transferable Neighborhood Discovery for Unsupervised Cross-domain Gait Recognition. ISCAS 2021"

Requirements

Conda
GPUs
Python 3.7
PyTorch 1.1.0

Installation

You can replace the second command from the bottom to install pytorch based on your CUDA version.

git clone https://github.com/JinkaiZheng/TraND.git
cd TraND
conda create --name py37torch110 python=3.7
conda activate py37torch110
conda install pytorch==1.1.0 torchvision==0.3.0 cudatoolkit=10.0 -c pytorch
pip install -r requirements

Data Preparation

Download CASIA-B and OU-LP

Data Pretreatment

pretreatment_casia.py and pretreatment_oulp.py use the alignment method in this paper. In the case of CASIA-B dataset, you need to run the command:

python GaitSet/pretreatment_casia.py --input_path='root_path_of_raw_dataset' --output_path='./data/CASIA-B'

Data Structrue

After the pretreatment, the data structure under the directory should like this

./data
├── CASIA-B
│  ├── 001
│     ├── bg-01
│        ├── 000
│           └── 001-bg-01-000-001.png
├── OULP
│  ├── 0000024
│     ├── Seq00
│        ├── 55
            └── 00000061.png

Train

Stage I: Supervised Prior Knowledge Learning on Source Domain

Training the GaitSet model in the source domain, run this command:

 python GaitSet/train.py --data "casia-b"

Stage II: Transferable Neighbor Discovery on Target Domain

Fine-tuning the GaitSet model in the target domain with TraND method, run this command:

sh Experement.sh

Test

Testing the model in self domain, such as CASIA-B dataset, run this command:

python GaitSet/test.py --data "casia-b"

Testing the model in cross domain, such as CASIA-B -> OU-LP dataset, run this command:

python GaitSet/test_cross.py --source "casia-b" --target "oulp"

Citation

Please cite this paper in your publications if it helps your research:

@article{DBLP:journals/corr/abs-2102-04621,
  author    = {Jinkai Zheng and
               Xinchen Liu and
               Chenggang Yan and
               Jiyong Zhang and
               Wu Liu and
               Xiaoping Zhang and
               Tao Mei},
  title     = {TraND: Transferable Neighborhood Discovery for Unsupervised Cross-domain
               Gait Recognition},
  journal   = {ISCAS},
  year      = {2021}
}

Acknowledgement

GaitSet
AND

KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Control

KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Control Tomas Jakab, Richard Tucker, Ameesh Makadia, Jiajun Wu, Noah Snavely, Angjoo Ka

87 Nov 30, 2022

Unsupervised Discovery of Object Radiance Fields

Unsupervised Discovery of Object Radiance Fields by Hong-Xing Yu, Leonidas J. Guibas and Jiajun Wu from Stanford University. arXiv link: https://arxiv

148 Nov 30, 2022

Pytorch implementation of the unsupervised object discovery method LOST.

LOST Pytorch implementation of the unsupervised object discovery method LOST. More details can be found in the paper: Localizing Objects with Self-Sup

189 Dec 25, 2022

Code for SentiBERT: A Transferable Transformer-Based Architecture for Compositional Sentiment Semantics (ACL'2020).

SentiBERT Code for SentiBERT: A Transferable Transformer-Based Architecture for Compositional Sentiment Semantics (ACL'2020). https://arxiv.org/abs/20

66 Aug 13, 2022

CLIP: Connecting Text and Image (Learning Transferable Visual Models From Natural Language Supervision)

CLIP (Contrastive Language–Image Pre-training) Experiments (Evaluation) Model Dataset Acc (%) ViT-B/32 (Paper) CIFAR100 65.1 ViT-B/32 (Our) CIFAR100 6

52 Jan 7, 2023

Official repository for "On Generating Transferable Targeted Perturbations" (ICCV 2021)

On Generating Transferable Targeted Perturbations (ICCV'21) Muzammal Naseer, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, and Fatih Porikli Paper:

46 Nov 17, 2022

TransPrompt - Towards an Automatic Transferable Prompting Framework for Few-shot Text Classification

TransPrompt This code is implement for our EMNLP 2021's paper 《TransPrompt：Towards an Automatic Transferable Prompting Framework for Few-shot Text Cla

23 Dec 21, 2022

Cross Quality LFW: A database for Analyzing Cross-Resolution Image Face Recognition in Unconstrained Environments

Cross-Quality Labeled Faces in the Wild (XQLFW) Here, we release the database, evaluation protocol and code for the following paper: Cross Quality LFW

10 Dec 12, 2022

“Data Augmentation for Cross-Domain Named Entity Recognition” (EMNLP 2021)

Data Augmentation for Cross-Domain Named Entity Recognition Authors: Shuguang Chen, Gustavo Aguilar, Leonardo Neves and Thamar Solorio This repository

18 Sep 10, 2022

Releases(V0.1)

V0.1(Sep 27, 2021)
CASIA_best_encoder.ptm: The best model of GaitSet model trained on the CASIA-B dataset.

OULP_best_encoder.ptm: The best model of GaitSet model trained on the OU-LP dataset.

CASIA2OULP_best_encoder.ptm: The best model of TraND model trained on the CASIA-B dataset and tested on the OU-LP dataset.

OULP2CASIA_best_encoder.ptm: The best model of TraND model trained on the OU-LP dataset and tested on the CASIA-B dataset.

Source code(tar.gz)
Source code(zip)
CASIA2OULP_best_encoder.ptm(24.08 MB)
CASIA_best_encoder.ptm(24.08 MB)
OULP2CASIA_best_encoder.ptm(24.08 MB)
OULP_best_encoder.ptm(24.08 MB)
segmentation_hrnet_best_model.pth(251.88 MB)

TraND: Transferable Neighborhood Discovery for Unsupervised Cross-domain Gait Recognition.

Related tags

Overview

TraND

Requirements

Installation

Data Preparation

Data Pretreatment

Data Structrue

Train

Stage I: Supervised Prior Knowledge Learning on Source Domain

Stage II: Transferable Neighbor Discovery on Target Domain

Test

Citation

Acknowledgement

You might also like...

KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Control

Unsupervised Discovery of Object Radiance Fields

Pytorch implementation of the unsupervised object discovery method LOST.

Code for SentiBERT: A Transferable Transformer-Based Architecture for Compositional Sentiment Semantics (ACL'2020).

CLIP: Connecting Text and Image (Learning Transferable Visual Models From Natural Language Supervision)

Official repository for "On Generating Transferable Targeted Perturbations" (ICCV 2021)

TransPrompt - Towards an Automatic Transferable Prompting Framework for Few-shot Text Classification

Cross Quality LFW: A database for Analyzing Cross-Resolution Image Face Recognition in Unconstrained Environments

“Data Augmentation for Cross-Domain Named Entity Recognition” (EMNLP 2021)

Releases(V0.1)

V0.1(Sep 27, 2021)

Owner

Jinkai Zheng

Code for the paper "VisualBERT: A Simple and Performant Baseline for Vision and Language"

Free-duolingo-plus - Duolingo account creator that uses your invite code to get you free duolingo plus

Code to run experiments in SLOE: A Faster Method for Statistical Inference in High-Dimensional Logistic Regression.

A program that can analyze videos according to the weights you select

Tutorial on active learning with the Nvidia Transfer Learning Toolkit (TLT).

Flickr-Faces-HQ (FFHQ) is a high-quality image dataset of human faces, originally created as a benchmark for generative adversarial networks (GAN)

Merlion: A Machine Learning Framework for Time Series Intelligence

TilinGNN: Learning to Tile with Self-Supervised Graph Neural Network (SIGGRAPH 2020)

BigbrotherBENL - Face recognition on the Big Brother episodes in Belgium and the Netherlands.

Realtime_Multi-Person_Pose_Estimation

It is a simple library to speed up CLIP inference up to 3x (K80 GPU)

Probabilistic Programming and Statistical Inference in PyTorch

Repository for the electrical and ICT benchmark model developed in the ERIGrid 2.0 project.

Scenarios, tutorials and demos for Autonomous Driving

Boost learning for GNNs from the graph structure under challenging heterophily settings. (NeurIPS'20)

Deep Illuminator is a data augmentation tool designed for image relighting. It can be used to easily and efficiently generate a wide range of illumination variants of a single image.

Code for generating the figures in the paper "Capacity of Group-invariant Linear Readouts from Equivariant Representations: How Many Objects can be Linearly Classified Under All Possible Views?"

CaFM-pytorch ICCV ACCEPT Introduction of dataset VSD4K

An Intelligent Self-driving Truck System For Highway Transportation

PyTorch implementation of DeepUME: Learning the Universal Manifold Embedding for Robust Point Cloud Registration (BMVC 2021)