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    |      *    |
     --------------------------------------------------------------

Noteļ¼š 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
ICCV2021 Expert-Goal Trajectory Prediction

ICCV 2021: Where are you heading? Dynamic Trajectory Prediction with Expert Goal Examples This repository contains the code for the paper Where are yo

hz 21 Dec 12, 2022
Autotype on websites that have copy-paste disabled like Moodle, HackerEarth contest etc.

Autotype A quick and small python script that helps you autotype on websites that have copy paste disabled like Moodle, HackerEarth contests etc as it

Tushar 32 Nov 03, 2022
Readings for "A Unified View of Relational Deep Learning for Polypharmacy Side Effect, Combination Therapy, and Drug-Drug Interaction Prediction."

Polypharmacy - DDI - Synergy Survey The Survey Paper This repository accompanies our survey paper A Unified View of Relational Deep Learning for Polyp

AstraZeneca 79 Jan 05, 2023
Charsiu: A transformer-based phonetic aligner

Charsiu: A transformer-based phonetic aligner [arXiv] Note. This is a preview version. The aligner is under active development. New functions, new lan

jzhu 166 Dec 09, 2022
This repository contains pre-trained models and some evaluation code for our paper Towards Unsupervised Dense Information Retrieval with Contrastive Learning

Contriever: Towards Unsupervised Dense Information Retrieval with Contrastive Learning This repository contains pre-trained models and some evaluation

Meta Research 207 Jan 08, 2023
Poplar implementation of "Bundle Adjustment on a Graph Processor" (CVPR 2020)

Poplar Implementation of Bundle Adjustment using Gaussian Belief Propagation on Graphcore's IPU Implementation of CVPR 2020 paper: Bundle Adjustment o

Joe Ortiz 34 Dec 05, 2022
Predict multi paths to a moving person depending on his trajectory history.

Multi-future Trajectory Prediction The project is about using the Multiverse model to make possible multible-future trajectory prediction for a seen p

Said Gamal 1 Jan 18, 2022
Aircraft design optimization made fast through modern automatic differentiation

Aircraft design optimization made fast through modern automatic differentiation. Plug-and-play analysis tools for aerodynamics, propulsion, structures, trajectory design, and much more.

Peter Sharpe 394 Dec 23, 2022
Pyeventbus: a publish/subscribe event bus

pyeventbus pyeventbus is a publish/subscribe event bus for Python 2.7. simplifies the communication between python classes decouples event senders and

15 Apr 21, 2022
PyTorch implementation of Off-policy Learning in Two-stage Recommender Systems

Off-Policy-2-Stage This repo provides a PyTorch implementation of the MovieLens experiments for the following paper: Off-policy Learning in Two-stage

Jiaqi Ma 25 Dec 12, 2022
Corruption Invariant Learning for Re-identification

Corruption Invariant Learning for Re-identification The official repository for Benchmarks for Corruption Invariant Person Re-identification (NeurIPS

Minghui Chen 73 Dec 08, 2022
Official codebase for "B-Pref: Benchmarking Preference-BasedReinforcement Learning" contains scripts to reproduce experiments.

B-Pref Official codebase for B-Pref: Benchmarking Preference-BasedReinforcement Learning contains scripts to reproduce experiments. Install conda env

48 Dec 20, 2022
(EI 2022) Controllable Confidence-Based Image Denoising

Image Denoising with Control over Deep Network Hallucination Paper and arXiv preprint -- Our frequency-domain insights derive from SFM and the concept

Images and Visual Representation Laboratory (IVRL) at EPFL 5 Dec 18, 2022
TakeInfoatNistforICS - Take Information in NIST NVD for ICS

Take Information in NIST NVD for ICS This project developed with Python. When yo

5 Sep 05, 2022
Visualize Camera's Pose Using Extrinsic Parameter by Plotting Pyramid Model on 3D Space

extrinsic2pyramid Visualize Camera's Pose Using Extrinsic Parameter by Plotting Pyramid Model on 3D Space Intro A very simple and straightforward modu

JEONG HYEONJIN 106 Dec 28, 2022
Vision transformers (ViTs) have found only limited practical use in processing images

CXV Convolutional Xformers for Vision Vision transformers (ViTs) have found only limited practical use in processing images, in spite of their state-o

Cloudwalker 23 Sep 10, 2022
This package contains a PyTorch Implementation of IB-GAN of the submitted paper in AAAI 2021

The PyTorch implementation of IB-GAN model of AAAI 2021 This package contains a PyTorch implementation of IB-GAN presented in the submitted paper (IB-

Insu Jeon 9 Mar 30, 2022
Telegram chatbot created with deep learning model (LSTM) and telebot library.

Telegram chatbot Telegram chatbot created with deep learning model (LSTM) and telebot library. Description This program will allow you to create very

1 Jan 04, 2022
NLU Dataset Diagnostics

NLU Dataset Diagnostics This repository contains data and scripts to reproduce the results from our paper: Aarne Talman, Marianna Apidianaki, Stergios

Language Technology at the University of Helsinki 1 Jul 20, 2022
Consecutive-Subsequence - Simple software to calculate susequence with highest sum

Simple software to calculate susequence with highest sum This repository contain

Gbadamosi Farouk 1 Jan 31, 2022