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

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

30 Apr 2020ECCV 2020 8arXiv:2004.14973archive 2025-07-28

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

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.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology: its page in Syntology's graph, with its repositories and citations.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

arjunmajum/vln-bert officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Vision and Language Navigation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Vision and Language Navigation VLN Challenge VLN-Bert error 3.09 #6 of 145 Archive leaderboard report
Vision and Language Navigation VLN Challenge VLN-Bert length 686.62 #6 of 145 Archive leaderboard report
Vision and Language Navigation VLN Challenge VLN-Bert oracle success 0.99 #6 of 145 Archive leaderboard report
Vision and Language Navigation VLN Challenge VLN-Bert spl 0.01 #6 of 145 Archive leaderboard report
Vision and Language Navigation VLN Challenge VLN-Bert success 0.73 #6 of 145 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections