AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model

Dilxat Muhtar, Zhenshi Li, Feng Gu, Xueliang Zhang, Pengfeng Xiao

ECCV 2024 · Vision-language and multimodal › Multimodal LLMs · approach: Instruction-tuned multimodal assistants · 152 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
RS-specific alignment and curriculum training (LHRS-Bot) vs general MLLMsLHRS-Bot · RS classification avg (7 datasets)average accuracy (%): 44.32 -> 71.83Improved
use LHRS-Align instead of RS5M for stage-1 alignment (ablation)LHRS-Bot · fMoWaccuracy (%): 42.68 -> 56.56Improved
use LHRS-Align instead of SkyScript for alignment (ablation)LHRS-Bot · fMoWaccuracy (%): 31.27 -> 56.56Improved
use LHRS-Align instead of RS5M on EuroSAT and WHU-RS19 (ablation)LHRS-Bot · EuroSATaccuracy (%): 54.92 -> 51.40Hurt
use multi-level features with descending query allocation instead of single-level MLP (ablation)LHRS-Bot · Visual groundingaverage accuracy (%): 75.97 -> 79.90Improved
use descending [64,48,32] instead of ascending [32,48,64] queries (ablation)LHRS-Bot · Classificationaverage accuracy (%): 60.68 -> 65.43Improved
use descending queries instead of identical 64 queries per level (ablation)LHRS-Bot · VQAaverage accuracy (%): 87.88 -> 90.14Improved
use token merging instead of perceiver for multi-level features (ablation)LHRS-Bot · Classificationaverage accuracy (%): 65.43 -> 49.51Hurt
use single-level MLP vs perceiver multi-level on high-level tasks (ablation)LHRS-Bot · VQAaverage accuracy (%): 90.06 vs 90.14No clear effect
LHRS-Bot vs RSGPT on RSVQA-LRLHRS-Bot · RSVQA-LRaverage accuracy (%): 92.29 -> 89.19Hurt

Later papers that compared with this method

4 later accepted papers report LHRS-Bot as a baseline in their results tables; 3 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 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