Code reproduce for paper "Vehicle Re-identification with Viewpoint-aware Metric Learning"

Related tags

Deep LearningVANET
Overview

VANET

Code reproduce for paper "Vehicle Re-identification with Viewpoint-aware Metric Learning"

Introduction

This is the implementation of article VANet "Vehicle Re-identification with Viewpoint-aware Metric Learning", which support both single-branch training and two branch training.

Implementation details

The whole implementation is based on PVEN project(https://github.com/silverbulletmdc/PVEN). The key code block added and modified are mainly distributed as follows:

For network construction:
    This project provide two version of backbone, namely 'googlenet' and 'resnet50' respectively. There the corresponding configuration files 
    as well as other corresponding code interfence are all provided completely.
    code location: vehicle_reid_pytorch/models/vanet.py

For training:
    This project provide two mode of training, namely 'single branch(baseline of VANet)' and 'two branch(VANet)' respectively
    code location: examples/parsing_reid/main_vanet_single_branch.py
    code location: examples/parsing_reid/main_vanet_two_branch.py

Configuration files:
    code location: examples/parsing_reid/configs/veri776_b64_baseline_vanet_single_branch_resnet.yml
    code location: examples/parsing_reid/configs/veri776_b64_baseline_vanet_two_branch_resnet.yml
    code location: examples/parsing_reid/configs/veri776_b64_baseline_vanet_two_branch_googlenet.yml

For loss calculation:
    code location: vehicle_reid_pytorch/loss/triplet_loss.py

For evaluation:
    mAP, cmc, ..., hist distribution figure drawing function are included.
    code location: examples/parsing_reid/math_tools.py

Results comparasion

We have achieved the following preformance by using the method this paper 'VANET' provided.

     -------------------------- -----------------------------------
                  |    mAP    |   rank-1  |   rank-5  |  rank-10  |
     --------------------------------- ----------------------------
      VANET+BOT   |   80.1%   |   96.5    |   98.5    |    99.4   | 
     --------------------------------------------------------------
      BOT(ours)   |   77.8%   |   95.3    |   97.8    |    98.8   |
     --------------------------------------------------------------
      BOT[1]      |   78.2%   |   95.5    |   97.9    |      *    |
     --------------------------------------------------------------

Note: The 'BOT', which means "bag of tricks" proposed by paper[2]. With respect to the two branch implementation of the above "VANET+BOT", we adopted the first 6 layers of the official resnet50 as the shared_conv network, the remaining two layers as the branch_conv network.There are also instructions in the corresponding code when you use.

Also, four type data's(similar-view_same-id, similar-view_different-id, different-view_different-id, different-view_same-id) distribution are drawn based on paper's aspect. note: this visualization code can be founded at examples/parsing_reid/math_tools.py

1. Get started

All the results are tested on VeRi-776 dstasets. Please reference to the environment implementation of other general reid projects, this project reference to fast-reid's.

2. Training

Reference to folder run_sh/run_main_XXX.sh Note: If you want to use your own dataset for training, remember to keep your data's structure be consistent with the veri776 dataloader's output in this project, reference to realted code for more details.

Example:

  sh ./run_sh/run_main_vanet_two_branch_resnet.sh

3. evaluation

Reference to folder run_sh/run_eval_XXX.sh Note: We have add 'drawing hist graph' function in evaluated stage, if you needn't this statistic operation temporarily, remember to shut down this function, for the operation is to some extent time-consuming, detail code block are located in examples/parsing_reid/math_tools.py.

Example:

  sh ./run_sh/run_eval_two_branch_resnet.sh

reference

[1] Khorramshahi, Pirazh, et al. "The devil is in the details: Self-supervised attention for vehicle re-identification." European Conference on Computer Vision. Springer, Cham, 2020.

[2] Luo, Hao, et al. "Bag of tricks and a strong baseline for deep person re-identification." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. 2019.

Contact

For any question, please file an issue or contact

Shichao Liu (Shanghai Em-Data Technology Co., Ltd.) [email protected]
Owner
EMDATA-AILAB
EMDATA-AILAB
Official source code of Fast Point Transformer, CVPR 2022

Fast Point Transformer Project Page | Paper This repository contains the official source code and data for our paper: Fast Point Transformer Chunghyun

182 Dec 23, 2022
A minimal yet resourceful implementation of diffusion models (along with pretrained models + synthetic images for nine datasets)

A minimal yet resourceful implementation of diffusion models (along with pretrained models + synthetic images for nine datasets)

Vikash Sehwag 65 Dec 19, 2022
Official code for paper "Optimization for Oriented Object Detection via Representation Invariance Loss".

Optimization for Oriented Object Detection via Representation Invariance Loss By Qi Ming, Zhiqiang Zhou, Lingjuan Miao, Xue Yang, and Yunpeng Dong. Th

ming71 56 Nov 28, 2022
CR-Fill: Generative Image Inpainting with Auxiliary Contextual Reconstruction. ICCV 2021

crfill Usage | Web App | | Paper | Supplementary Material | More results | code for paper ``CR-Fill: Generative Image Inpainting with Auxiliary Contex

182 Dec 20, 2022
URIE: Universal Image Enhancementfor Visual Recognition in the Wild

URIE: Universal Image Enhancementfor Visual Recognition in the Wild This is the implementation of the paper "URIE: Universal Image Enhancement for Vis

Taeyoung Son 43 Sep 12, 2022
PyTorch trainer and model for Sequence Classification

PyTorch-trainer-and-model-for-Sequence-Classification After cloning the repository, modify your training data so that the training data is a .csv file

NhanTieu 2 Dec 09, 2022
Code for "Unsupervised Source Separation via Bayesian inference in the latent domain"

LQVAE-separation Code for "Unsupervised Source Separation via Bayesian inference in the latent domain" Paper Samples GT Compressed Separated Drums GT

Michele Mancusi 30 Oct 25, 2022
PyTorch implementation of TSception V2 using DEAP dataset

TSception This is the PyTorch implementation of TSception V2 using DEAP dataset in our paper: Yi Ding, Neethu Robinson, Su Zhang, Qiuhao Zeng, Cuntai

Yi Ding 27 Dec 15, 2022
Simple helper library to convert a collection of numpy data to tfrecord, and build a tensorflow dataset from the tfrecord.

numpy2tfrecord Simple helper library to convert a collection of numpy data to tfrecord, and build a tensorflow dataset from the tfrecord. Installation

Ryo Yonetani 2 Jan 16, 2022
RealTime Emotion Recognizer for Machine Learning Study Jam's demo

Emotion recognizer Table of contents Clone project Dataset Install dependencies Main program Demo 1. Clone project git clone https://github.com/GDSC20

Google Developer Student Club - UIT 1 Oct 05, 2021
Supervised domain-agnostic prediction framework for probabilistic modelling

A supervised domain-agnostic framework that allows for probabilistic modelling, namely the prediction of probability distributions for individual data

The Alan Turing Institute 112 Oct 23, 2022
Fuzzer for Linux Kernel Drivers

difuze: Fuzzer for Linux Kernel Drivers This repo contains all the sources (including setup scripts), you need to get difuze up and running. Tested on

seclab 344 Dec 27, 2022
The Balloon Learning Environment - flying stratospheric balloons with deep reinforcement learning.

Balloon Learning Environment Docs The Balloon Learning Environment (BLE) is a simulator for stratospheric balloons. It is designed as a benchmark envi

Google 87 Dec 25, 2022
SSD: A Unified Framework for Self-Supervised Outlier Detection [ICLR 2021]

SSD: A Unified Framework for Self-Supervised Outlier Detection [ICLR 2021] Pdf: https://openreview.net/forum?id=v5gjXpmR8J Code for our ICLR 2021 pape

Princeton INSPIRE Research Group 113 Nov 27, 2022
An Industrial Grade Federated Learning Framework

DOC | Quick Start | 中文 FATE (Federated AI Technology Enabler) is an open-source project initiated by Webank's AI Department to provide a secure comput

Federated AI Ecosystem 4.8k Jan 09, 2023
[arXiv'22] Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation

Panoptic NeRF Project Page | Paper | Dataset Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation Xiao Fu*, Shangzhan zhang*,

Xiao Fu 111 Dec 16, 2022
Code for WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models.

WECHSEL Code for WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models. arXiv: https://arx

Institute of Computational Perception 45 Dec 29, 2022
Code/data of the paper "Hand-Object Contact Prediction via Motion-Based Pseudo-Labeling and Guided Progressive Label Correction" (BMVC2021)

Hand-Object Contact Prediction (BMVC2021) This repository contains the code and data for the paper "Hand-Object Contact Prediction via Motion-Based Ps

Takuma Yagi 13 Nov 07, 2022
This is an example of object detection on Micro bacterium tuberculosis using Mask-RCNN

Mask-RCNN on Mycobacterium tuberculosis This is an example of object detection on Mycobacterium Tuberculosis using Mask RCNN. Implement of Mask R-CNN

Jun-En Ding 1 Sep 16, 2021