AI Paper Atlas

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

Less Is More: Generating Grounded Navigation Instructions From Landmarks

Su Wang, Ceslee Montgomery, Jordi Orbay, Vighnesh Birodkar, Aleksandra Faust, Izzeddin Gur, Natasha Jaques, Austin Waters, Jason Baldridge, Peter Anderson

CVPR 2022 · Vision-language and multimodal › Robot action and navigation · approach: Pretraining and data augmentation for VLN · 44 citations (OpenAlex)

Check 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
Train on RxR rather than R2RSpkFol · R2R Val-UnseenSR: 42.0% → 57.8%Improved
Use selected visual landmarks rather than full panoramic inputs (ablation)MARKY-MT5 · R2R Val-UnseenSR: 57.8% → 70.8%Improved
Replace outbound-only inputs with silver landmark inputs (ablation)MARKY-MT5 · RxR Val-UnseenSR: 53.3% → 63.3%Improved
Replace detector-predicted landmarks with silver landmarks (ablation)MARKY-MT5 · RxR Val-UnseenSR: 61.5% vs. 63.3%Improved
Add the rewrite auxiliary task (ablation)MARKY-MT5 with silver landmark inputs · RxR Val-UnseenBLEU: +1.8Improved
Add CC3M/CC12M pretraining (ablation)MARKY-MT5 with silver landmarks and rewrite task · RxR Val-UnseenBLEU: +0.5Improved
Add CC3M/CC12M pretraining (ablation)MARKY-MT5 with silver landmarks and rewrite task · RxR Val-UnseenSPICE (en): -0.2Hurt
Use detector-predicted instead of silver landmarks (ablation)MARKY-MT5 · RxR Val-UnseenBLEU: 13.4 → 5.8Hurt
Add timestamp-based bias to landmark grounding (ablation)MURAL landmark alignment · 100 RxR Val-Unseen instructionsalignment precision: 49.6 w/o bias vs. 56.5 w/ biasImproved
Use timestamp bias alone without MURAL image-text scores (ablation)MURAL landmark alignment · 100 RxR Val-Unseen instructionsalignment precision: 23.4 precisionHurt

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