AR/VR

RESEARCH

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

August 23, 2020

Abstract

Following a navigation instruction such as 'Walk down the stairs and stop at the brown sofa' requires embodied AI agents to ground scene elements referenced via language (e.g. 'stairs') to visual content in the environment (pixels corresponding to 'stairs'). We ask the following question -- can we leverage abundant 'disembodied' web-scraped vision-and-language corpora (e.g. Conceptual Captions) to learn visual groundings (what do 'stairs' look like?) that improve performance on a relatively data-starved embodied perception task (Vision-and-Language Navigation)? Specifically, we develop VLN-BERT, a visiolinguistic transformer-based model for scoring the compatibility between an instruction ('...stop at the brown sofa') and a sequence of panoramic RGB images captured by the agent. We demonstrate that pretraining VLN-BERT on image-text pairs from the web before fine-tuning on embodied path-instruction data significantly improves performance on VLN -- outperforming the prior state-of-the-art in the fully-observed setting by 4 absolute percentage points on success rate. Ablations of our pretraining curriculum show each stage to be impactful -- with their combination resulting in further positive synergistic effects.

Download the Paper

AUTHORS

Written by

Dhruv Batra

Devi Parikh

Arjun Majumdar

Ayush Shrivastava

Peter Anderson

Stefan Lee

Publisher

ECCV

Related Publications

June 11, 2025

RESEARCH

COMPUTER VISION

IntPhys 2: Benchmarking Intuitive Physics Understanding In Complex Synthetic Environments

Florian Bordes, Quentin Garrido, Justine Kao, Adina Williams, Mike Rabbat, Emmanuel Dupoux

June 11, 2025

June 11, 2025

RESEARCH

COMPUTER VISION

A Shortcut-aware Video-QA Benchmark for Physical Understanding via Minimal Video Pairs

Benno Krojer, Mojtaba Komeili, Candace Ross, Quentin Garrido, Koustuv Sinha, Nicolas Ballas, Mido Assran

June 11, 2025

June 11, 2025

ROBOTICS

RESEARCH

V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning

Mido Assran, Adrien Bardes, David Fan, Quentin Garrido, Russell Howes, Mojtaba Komeili, Matthew Muckley, Ammar Rizvi, Claire Roberts, Koustuv Sinha, Artem Zholus, Sergio Arnaud, Abha Gejji, Ada Martin, Francois Robert Hogan, Daniel Dugas, Piotr Bojanowski, Vasil Khalidov, Patrick Labatut, Francisco Massa, Marc Szafraniec, Kapil Krishnakumar, Yong Li, Xiaodong Ma, Sarath Chandar, Franziska Meier, Yann LeCun, Michael Rabbat, Nicolas Ballas

June 11, 2025

May 14, 2025

RESEARCH

CORE MACHINE LEARNING

UMA: A Family of Universal Models for Atoms

Brandon M. Wood, Misko Dzamba, Xiang Fu, Meng Gao, Muhammed Shuaibi, Luis Barroso-Luque, Kareem Abdelmaqsoud, Vahe Gharakhanyan, John R. Kitchin, Daniel S. Levine, Kyle Michel, Anuroop Sriram, Taco Cohen, Abhishek Das, Ammar Rizvi, Sushree Jagriti Sahoo, Zachary W. Ulissi, C. Lawrence Zitnick

May 14, 2025

Help Us Pioneer The Future of AI

We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.