Code for the paper "Improving Vision-and-Language Navigation with Image-Text Pairs from the Web" (ECCV 2020)

Related tags

Deep Learningvln-bert
Overview

Improving Vision-and-Language Navigation with Image-Text Pairs from the Web

Arjun Majumdar, Ayush Shrivastava, Stefan Lee, Peter Anderson, Devi Parikh, and Dhruv Batra

Paper: https://arxiv.org/abs/2004.14973

Model Zoo

A variety of pre-trained VLN-BERT weights can accessed through the following links:

Pre-training Stages Job ID Val Unseen SR URL
0 no pre-training 174631 30.52% TBD
1 1 175134 45.17% TBD
3 1 and 2 221943 49.64% download
2 1 and 3 220929 50.02% download
4 1, 2, and 3 (Full Model) 220825 59.26% download

Usage Instructions

Follow the instructions in INSTALL.md to setup this codebase. The instructions walk you through several steps including preprocessing the Matterport3D panoramas by extracting regions with a pretrained object detector.

Training

To preform stage 3 of pre-training, first download ViLBERT weights from here. Then, run:

python \
-m torch.distributed.launch \
--nproc_per_node=8 \
--nnodes=1 \
--node_rank=0 \
train.py \
--from_pretrained <path/to/vilbert_pytorch_model_9.bin> \
--save_name [pre_train_run_id] \
--num_epochs 50 \
--warmup_proportion 0.08 \
--cooldown_factor 8 \
--masked_language \
--masked_vision \
--no_ranking

To fine-tune VLN-BERT for the path selection task, run:

python \
-m torch.distributed.launch \
--nproc_per_node=8 \
--nnodes=1 \
--node_rank=0 \
train.py \
--from_pretrained <path/to/pytorch_model_50.bin> \
--save_name [fine_tune_run_id]

Evaluation

To evaluate a pre-trained model, run:

python test.py \
--split [val_seen|val_unseen] \
--from_pretrained <path/to/run_[run_id]_pytorch_model.bin> \
--save_name [run_id]

followed by:

python scripts/calculate-metrics.py <path/to/results_[val_seen|val_unseen].json>

Citation

If you find this code useful, please consider citing:

@inproceedings{majumdar2020improving,
  title={Improving Vision-and-Language Navigation with Image-Text Pairs from the Web},
  author={Arjun Majumdar and Ayush Shrivastava and Stefan Lee and Peter Anderson and Devi Parikh and Dhruv Batra},
  booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},
  year={2020}
}
Owner
Arjun Majumdar
PhD student at Georgia Tech.
Arjun Majumdar
Explicable Reward Design for Reinforcement Learning Agents [NeurIPS'21]

Explicable Reward Design for Reinforcement Learning Agents [NeurIPS'21]

3 May 12, 2022
Easy Parallel Library (EPL) is a general and efficient deep learning framework for distributed model training.

English | 简体中文 Easy Parallel Library Overview Easy Parallel Library (EPL) is a general and efficient library for distributed model training. Usability

Alibaba 185 Dec 21, 2022
QRec: A Python Framework for quick implementation of recommender systems (TensorFlow Based)

Introduction QRec is a Python framework for recommender systems (Supported by Python 3.7.4 and Tensorflow 1.14+) in which a number of influential and

Yu 1.4k Dec 30, 2022
Revisiting Global Statistics Aggregation for Improving Image Restoration

Revisiting Global Statistics Aggregation for Improving Image Restoration Xiaojie Chu, Liangyu Chen, Chengpeng Chen, Xin Lu Paper: https://arxiv.org/pd

MEGVII Research 128 Dec 24, 2022
GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training @ KDD 2020

GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training Original implementation for paper GCC: Graph Contrastive Coding for Graph Neural N

THUDM 274 Dec 27, 2022
EDPN: Enhanced Deep Pyramid Network for Blurry Image Restoration

EDPN: Enhanced Deep Pyramid Network for Blurry Image Restoration Ruikang Xu, Zeyu Xiao, Jie Huang, Yueyi Zhang, Zhiwei Xiong. EDPN: Enhanced Deep Pyra

69 Dec 15, 2022
Accelerate Neural Net Training by Progressively Freezing Layers

FreezeOut A simple technique to accelerate neural net training by progressively freezing layers. This repository contains code for the extended abstra

Andy Brock 203 Jun 19, 2022
Assessing the Influence of Models on the Performance of Reinforcement Learning Algorithms applied on Continuous Control Tasks

Assessing the Influence of Models on the Performance of Reinforcement Learning Algorithms applied on Continuous Control Tasks This is the master thesi

Giacomo Arcieri 1 Mar 21, 2022
Face recognition. Redefined.

FaceFinder Use a powerful CNN to identify faces in images! TABLE OF CONTENTS About The Project Built With Getting Started Prerequisites Installation U

BleepLogger 20 Jun 16, 2021
I explore rock vs. mine prediction using a SONAR dataset

I explore rock vs. mine prediction using a SONAR dataset. Using a Logistic Regression Model for my prediction algorithm, I intend on predicting what an object is based on supervised learning.

Jeff Shen 1 Jan 11, 2022
GenshinMapAutoMarkTools - Tools To add/delete/refresh resources mark in Genshin Impact Map

使用说明 适配 windows7以上 64位 原神1920x1080窗口(其他分辨率后续适配) 待更新渊下宫 English version is to be

Zero_Circle 209 Dec 28, 2022
An efficient toolkit for Face Stylization based on the paper "AgileGAN: Stylizing Portraits by Inversion-Consistent Transfer Learning"

MMGEN-FaceStylor English | 简体中文 Introduction This repo is an efficient toolkit for Face Stylization based on the paper "AgileGAN: Stylizing Portraits

OpenMMLab 182 Dec 27, 2022
Robotic Process Automation in Windows and Linux by using Driagrams.net BPMN diagrams.

BPMN_RPA Robotic Process Automation in Windows and Linux by using BPMN diagrams. With this Framework you can draw Business Process Model Notation base

23 Dec 14, 2022
This is the reference implementation for "Coresets via Bilevel Optimization for Continual Learning and Streaming"

Coresets via Bilevel Optimization This is the reference implementation for "Coresets via Bilevel Optimization for Continual Learning and Streaming" ht

Zalán Borsos 51 Dec 30, 2022
a delightful machine learning tool that allows you to train, test and use models without writing code

igel A delightful machine learning tool that allows you to train/fit, test and use models without writing code Note I'm also working on a GUI desktop

Nidhal Baccouri 3k Jan 05, 2023
The audio-video synchronization of MKV Container Format is exploited to achieve data hiding

The audio-video synchronization of MKV Container Format is exploited to achieve data hiding, where the hidden data can be utilized for various management purposes, including hyper-linking, annotation

Maxim Zaika 1 Nov 17, 2021
Pytorch implementation of the paper DocEnTr: An End-to-End Document Image Enhancement Transformer.

DocEnTR Description Pytorch implementation of the paper DocEnTr: An End-to-End Document Image Enhancement Transformer. This model is implemented on to

Mohamed Ali Souibgui 74 Jan 07, 2023
Real life contra a deep learning project built using mediapipe and openc

real-life-contra Description A python script that translates the body movement into in game control. Welcome to all new real life contra a deep learni

Programminghut 7 Jan 26, 2022
RAANet: Range-Aware Attention Network for LiDAR-based 3D Object Detection with Auxiliary Density Level Estimation

RAANet: Range-Aware Attention Network for LiDAR-based 3D Object Detection with Auxiliary Density Level Estimation Anonymous submission Abstract 3D obj

30 Sep 16, 2022
Implements the training, testing and editing tools for "Pluralistic Image Completion"

Pluralistic Image Completion ArXiv | Project Page | Online Demo | Video(demo) This repository implements the training, testing and editing tools for "

Chuanxia Zheng 615 Dec 08, 2022