AirLoop: Lifelong Loop Closure Detection

Overview

AirLoop

This repo contains the source code for paper:

Dasong Gao, Chen Wang, Sebastian Scherer. "AirLoop: Lifelong Loop Closure Detection." arXiv preprint arXiv:2109.08975 (2021).

Watch on YouTube

Demo

Examples of loop closure detection on each dataset. Note that our model is able to handle cross-environment loop closure detection despite only trained in individual environments sequentially:

Improved loop closure detection on TartanAir after extended training:

Usage

Dependencies

  • Python >= 3.5
  • PyTorch < 1.8
  • OpenCV >= 3.4
  • NumPy >= 1.19
  • Matplotlib
  • ConfigArgParse
  • PyYAML
  • tqdm

Data

We used the following subsets of datasets in our expriments:

  • TartanAir
    • Train/Test: abandonedfactory_night, carwelding, neighborhood, office2, westerndesert;
  • RobotCar
    • Train: 2014-11-28-12-07-13, 2014-12-10-18-10-50, 2014-12-16-09-14-09;
    • Test: 2014-06-24-14-47-45, 2014-12-05-15-42-07, 2014-12-16-18-44-24;
  • Nordland
    • Train/Test: All four seasons with recommended splits.

The datasets are aranged as follows:

$DATASET_ROOT/
├── tartanair/
│   ├── abandonedfactory_night/
│   └── ...
├── robotcar/
│   ├── train/
│   │   ├── 2014-11-28-12-07-13/
│   │   └── ...
│   └── test/
│       ├── 2014-06-24-14-47-45/
│       └── ...
└── nordland/
    ├── train/
    │   ├── fall_images_train/
    │   └── ...
    └── test/
        ├── fall_images_test/
        └── ...

Configuration

The following values in config/config.yaml need to be set:

  • dataset-root: The parent directory to all datasets ($DATASET_ROOT above);
  • catalog-dir: An (initially empty) directory for caching processed dataset index;
  • eval-gt-dir: An (initially empty) directory for groundtruth produced during evaluation.

Commandline

The following command will train a model sequentially (except for joint) in the specified envronments and evaluate the performance:

$ python main.py --dataset <tartanair/robotcar/nordland> --out-dir <OUT_DIR> --envs <LIST_OF_ENVIRONMENTS> --epochs <LIST_OF_EPOCHS> --method <finetune/si/ewc/kd/rkd/mas/rmas/airloop/joint>

--skip-train and --skip-eval can be specified to skip the train/test phase.

Owner
Chen Wang
I am engaged in delivering simple and efficient source code.
Chen Wang
1st Solution For ICDAR 2021 Competition on Mathematical Formula Detection

This project releases our 1st place solution on ICDAR 2021 Competition on Mathematical Formula Detection. We implement our solution based on MMDetection, which is an open source object detection tool

yuxzho 94 Dec 25, 2022
[Nature Machine Intelligence' 21] "Advancing COVID-19 Diagnosis with Privacy-Preserving Collaboration in Artificial Intelligence"

[UCADI] COVID-19 Diagnosis With Federated Learning Intro We developed a Federated Learning (FL) Framework for global researchers to collaboratively tr

HUST EIC AI-LAB 30 Dec 12, 2022
Code for the CVPR2021 workshop paper "Noise Conditional Flow Model for Learning the Super-Resolution Space"

NCSR: Noise Conditional Flow Model for Learning the Super-Resolution Space Official NCSR training PyTorch Code for the CVPR2021 workshop paper "Noise

57 Oct 03, 2022
This project uses ViT to perform image classification tasks on DATA set CIFAR10.

Vision-Transformer-Multiprocess-DistributedDataParallel-Apex Introduction This project uses ViT to perform image classification tasks on DATA set CIFA

Kaicheng Yang 3 Jun 03, 2022
Self-labelling via simultaneous clustering and representation learning. (ICLR 2020)

Self-labelling via simultaneous clustering and representation learning 🆗 🆗 🎉 NEW models (20th August 2020): Added standard SeLa pretrained torchvis

Yuki M. Asano 469 Jan 02, 2023
Python based Advanced AI Assistant

Knick is a virtual artificial intelligence project, fully developed in python. The objective of this project is to develop a virtual assistant that can handle our minor, intermediate as well as heavy

19 Nov 15, 2022
A (PyTorch) imbalanced dataset sampler for oversampling low frequent classes and undersampling high frequent ones.

Imbalanced Dataset Sampler Introduction In many machine learning applications, we often come across datasets where some types of data may be seen more

Ming 2k Jan 08, 2023
An executor that loads ONNX models and embeds documents using the ONNX runtime.

ONNXEncoder An executor that loads ONNX models and embeds documents using the ONNX runtime. Usage via Docker image (recommended) from jina import Flow

Jina AI 2 Mar 15, 2022
Realtime micro-expression recognition using OpenCV and PyTorch

Micro-expression Recognition Realtime micro-expression recognition from scratch using OpenCV and PyTorch Try it out with a webcam or video using the e

Irfan 35 Dec 05, 2022
Learning Domain Invariant Representations in Goal-conditioned Block MDPs

Learning Domain Invariant Representations in Goal-conditioned Block MDPs Beining Han, Chongyi Zheng, Harris Chan, Keiran Paster, Michael R. Zhang, Jim

Chongyi Zheng 3 Apr 12, 2022
Robotics environments

Robotics environments Details and documentation on these robotics environments are available in OpenAI's blog post and the accompanying technical repo

Farama Foundation 121 Dec 28, 2022
Code for our ICASSP 2021 paper: SA-Net: Shuffle Attention for Deep Convolutional Neural Networks

SA-Net: Shuffle Attention for Deep Convolutional Neural Networks (paper) By Qing-Long Zhang and Yu-Bin Yang [State Key Laboratory for Novel Software T

Qing-Long Zhang 199 Jan 08, 2023
A simple python library for fast image generation of people who do not exist.

Random Face A simple python library for fast image generation of people who do not exist. For more details, please refer to the [paper](https://arxiv.

Sergei Belousov 170 Dec 15, 2022
利用yolov5和TensorRT从0到1实现目标检测的模型训练到模型部署全过程

写在前面 利用TensorRT加速推理速度是以时间换取精度的做法,意味着在推理速度上升的同时将会有精度的下降,不过不用太担心,精度下降微乎其微。此外,要有NVIDIA显卡,经测试,CUDA10.2可以支持20系列显卡及以下,30系列显卡需要CUDA11.x的支持,并且目前有bug。 默认你已经完成了

Helium 6 Jul 28, 2022
Our VMAgent is a platform for exploiting Reinforcement Learning (RL) on Virtual Machine (VM) scheduling tasks.

VMAgent is a platform for exploiting Reinforcement Learning (RL) on Virtual Machine (VM) scheduling tasks. VMAgent is constructed based on one month r

56 Dec 12, 2022
Block-wisely Supervised Neural Architecture Search with Knowledge Distillation (CVPR 2020)

DNA This repository provides the code of our paper: Blockwisely Supervised Neural Architecture Search with Knowledge Distillation. Illustration of DNA

Changlin Li 215 Dec 19, 2022
ComputerVision - This repository aims at realized easy network architecture

ComputerVision This repository aims at realized easy network architecture Colori

DongDong 4 Dec 14, 2022
GAN-based Matrix Factorization for Recommender Systems

GAN-based Matrix Factorization for Recommender Systems This repository contains the datasets' splits, the source code of the experiments and their res

Ervin Dervishaj 9 Nov 06, 2022
Official repository of ICCV21 paper "Viewpoint Invariant Dense Matching for Visual Geolocalization"

Viewpoint Invariant Dense Matching for Visual Geolocalization: PyTorch implementation This is the implementation of the ICCV21 paper: G Berton, C. Mas

Gabriele Berton 44 Jan 03, 2023
A selection of State Of The Art research papers (and code) on human locomotion (pose + trajectory) prediction (forecasting)

A selection of State Of The Art research papers (and code) on human trajectory prediction (forecasting). Papers marked with [W] are workshop papers.

Karttikeya Manglam 40 Nov 18, 2022