AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

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

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

ECCV 2020 · Vision-language and multimodal › Robot action and navigation · approach: Pretraining and data augmentation for VLN · 209 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add language-only pretraining (BERT) (ablation)VLN-BERT · R2R val unseen (path selection)SR (%): 30.52 -> 45.17Improved
add visual grounding pretraining on web image-text pairs after language pretraining (ablation)VLN-BERT · R2R val unseen (path selection)SR (%): 45.17 -> 49.64Improved
add action grounding pretraining after language pretraining (ablation)VLN-BERT · R2R val unseen (path selection)SR (%): 45.17 -> 50.02Improved
add both visual and action grounding stages (ablation)VLN-BERT · R2R val unseen (path selection)SR (%): 45.17 -> 59.26Improved
add visual grounding stage to the full curriculum (ablation)VLN-BERT · R2R val unseen (path selection)SR (%): 50.02 -> 59.26Improved
add action grounding stage to the full curriculum (ablation)VLN-BERT · R2R val unseen (path selection)SR (%): 49.64 -> 59.26Improved
full pretraining curriculum vs none (ablation)VLN-BERT · R2R val unseen (path selection)SPL: 0.27 -> 0.55Improved
full pretraining curriculum vs none (ablation)VLN-BERT · R2R val unseen (path selection)NE (m): 6.81 -> 4.10Improved
add VLN-BERT to speaker + follower ensemblespeaker + follower · R2R val unseen (path selection)SR (%): 67.90 -> 73.61Improved
add a second randomly seeded follower to ensemblespeaker + follower · R2R val unseen (path selection)SR (%): 67.90 -> 69.14Improved
add a second speaker to ensemblespeaker + follower · R2R val unseen (path selection)SR (%): 67.90 -> 70.58Improved
replace follower/speaker single model with VLN-BERTsingle model re-ranking · R2R val unseen (path selection)SR (%): 54.66 -> 59.26Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy