AI Paper Atlas

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

Correctable Landmark Discovery via Large Models for Vision-Language Navigation

Bingqian Lin, Yunshuang Nie, Ziming Wei, Yi Zhu, Hang Xu, Shikui Ma, Jianzhuang Liu, Xiaodan Liang

TPAMI 2024 · Vision-language and multimodal › Robot action and navigation · approach: Reasoning-enhanced vision-language navigation · 30 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 learnable cooccurrence scoring (LS) (ablation)CONSOLE on DUET · R2R val unseenSPL (%): 60.64 -> 61.51Improved
add learnable cooccurrence scoring (LS) (ablation)CONSOLE on DUET · REVERIE val unseenSR (%): 48.68 -> 49.42Improved
add observation enhancement (OE) (ablation)CONSOLE on DUET · R2R val unseenSPL (%): 61.51 -> 63.02Improved
add observation enhancement (OE) (ablation)CONSOLE on HAMT · R2R val unseenSPL (%): 62.59 -> 63.06Improved
use 5 landmark cooccurrences instead of none (ablation)CONSOLE on HAMT · R2R val unseenSPL (%): 61.78 -> 62.42Improved
increase cooccurrence number from 5 to 10 (ablation)CONSOLE on HAMT · R2R val unseenSPL (%): 62.42 -> 62.19No clear effect
add landmark shifting instead of global landmark use (ablation)CONSOLE on HAMT · R2R val unseenSPL (%): 61.51 -> 62.42Improved
use summation instead of concatenation to fuse landmark and observation features (ablation)CONSOLE on HAMT · R2R val unseenSPL (%): 61.12 -> 62.59Improved
use loss weights 0.1 and 0.1 instead of 1 and 1 (ablation)CONSOLE on HAMT · R2R val unseenSPL (%): 62.26 -> 63.06Improved
set temperature 0.5 instead of 1 (ablation)CONSOLE on HAMT · R2R val unseenSPL (%): 63.10 -> 63.06No clear effect
use ChatGPT instead of Spacy for landmark extraction (ablation)CONSOLE on DUET · R2R val unseenSPL (%): 61.33 -> 63.02Improved
use ChatGPT instead of Vicuna13B for landmark extraction (ablation)CONSOLE on DUET · R2R val unseenSPL (%): 62.14 -> 63.02Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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