AI Paper Atlas

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

Cross-Modal Map Learning for Vision and Language Navigation

Georgios Georgakis, Karl Schmeckpeper, Karan Wanchoo, Soham Dan, Eleni Miltsakaki, Dan Roth, Kostas Daniilidis

CVPR 2022 · Vision-language and multimodal › Robot action and navigation · approach: Pretraining and data augmentation for VLN · 78 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
Use ground-truth local semantic maps instead of predicted mapsCM² · VLN-CE val-seenSR (%): 42.9 -> 52.8Improved
Use cross-modal map attention to condition map prediction on the instruction (ablation)CM² · VLN-CE map and waypoint predictionIoU (%): 21.2 -> 28.3Improved
Use cross-modal map attention to condition map prediction on the instruction (ablation)CM² · VLN-CE map and waypoint predictionF1 (%): 33.2 -> 42.2Improved
Use cross-modal map attention to condition map prediction on the instruction (ablation)CM² · VLN-CE map and waypoint predictionPCW (%): 71.1 -> 76.5Improved
Raise stop distance threshold from τ=0.5 to τ=1.5 (ablation)CM²-GT · VLN-CE val-seenSR (%): 52.8 -> 49.5Hurt
Raise stop distance threshold from τ=0.5 to τ=1.5 (ablation)CM²-GT · VLN-CE val-seenSPL (%): 41.8 -> 45.1Improved
Increase map size from 192 × 192 to 384 × 384 (ablation)CM²-GT · VLN-CE val-seenSR (%): 52.8 -> 58.4Improved
Increase map size from 192 × 192 to 384 × 384 (ablation)CM²-GT · VLN-CE val-seenNE (m): 4.81 -> 4.52Improved
Add starting position heatmap to path prediction (ablation)CM²-GT · VLN-CE val-seenSR (%): 34.3 -> 52.8Improved
Add traversed-waypoint auxiliary loss (ablation)CM²-GT · VLN-CE val-seenSR (%): 49.1 -> 52.8Improved
Remove both the starting position heatmap and traversed-waypoint auxiliary loss (ablation)CM²-GT · VLN-CE val-seenSR (%): 52.8 -> 29.3Hurt
Use CM² rather than LAWVLN-CE navigation · VLN-CE val-seenSR (%): 40.0 -> 42.9Improved

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