AI Paper Atlas

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

GridMM: Grid Memory Map for Vision-and-Language Navigation

Zihan Wang, Xiangyang Li, Jiahao Yang, Yeqi Liu, Shuqiang Jiang

ICCV 2023 · Vision-language and multimodal › Robot action and navigation · approach: Reasoning-enhanced vision-language navigation · 123 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 any map (topological, semantic, object, grid) over no map (ablation)GridMM base model · R2R-CE val unseenSR: 45.19 -> 47.02Improved
use grid features instead of top-down semantic map features (ablation)GridMM · R2R-CE val unseenSR: 46.36 -> 49.05Improved
use CLIP grid features instead of detected object features (ablation)GridMM · R2R-CE val unseenSR: 47.61 -> 49.05Improved
use egocentric relative coordinates instead of absolute coordinates (ablation)GridMM · R2R-CE val unseenSR: 48.72 -> 49.05Improved
add navigation trajectory memory (ablation)GridMM · R2R-CE val unseenSR: 47.42 -> 49.05Improved
use instruction relevance aggregation instead of average pooling (ablation)GridMM · R2R-CE val unseenSR: 48.63 -> 49.05Improved
increase map scale from 14x14 to 20x20 (ablation)GridMM · R2R-CE val unseenSR: 49.05 -> 49.86Mixed
decrease map scale from 14x14 to 8x8 (ablation)GridMM · R2R-CE val unseenSR: 49.05 -> 47.07Hurt
GridMM versus DUET on REVERIE val unseenGridMM · REVERIE val unseenSR: 46.98 -> 51.37Improved
GridMM versus BEVBert on REVERIE val unseenGridMM · REVERIE val unseenSR: 51.78 vs 51.37No clear effect
GridMM versus DUET on SOON test unseenGridMM · SOON test unseenSPL: 21.42 -> 21.25No clear effect

Later papers that compared with this method

5 later accepted papers report GridMM as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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