Saved in:
Bibliographic Details
Main Authors: Chen, Jian, Zhou, Peilin, Hua, Yining, Chong, Dading, Cao, Meng, Li, Yaowei, Chen, Wei, Zhu, Bing, Liang, Junwei, Yuan, Zixuan
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.09838
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909988020027392
author Chen, Jian
Zhou, Peilin
Hua, Yining
Chong, Dading
Cao, Meng
Li, Yaowei
Chen, Wei
Zhu, Bing
Liang, Junwei
Yuan, Zixuan
author_facet Chen, Jian
Zhou, Peilin
Hua, Yining
Chong, Dading
Cao, Meng
Li, Yaowei
Chen, Wei
Zhu, Bing
Liang, Junwei
Yuan, Zixuan
contents Meteorological heatmaps play a vital role in deciphering extreme weather phenomena, yet their inherent complexities marked by irregular contours, unstructured patterns, and complex color variations present unique analytical hurdles for state-of-the-art Vision-Language Models (VLMs). Current state-of-the-art models like GPT-4o, Qwen-VL, and LLaVA 1.6 struggle with tasks such as precise color identification and spatial localization, resulting in inaccurate or incomplete interpretations. To address these challenges, we introduce Sparse Position and Outline Tracking (SPOT), a novel algorithm specifically designed to process irregularly shaped colored regions in visual data. SPOT identifies and localizes these regions by extracting their spatial coordinates, enabling structured representations of irregular shapes. Building on SPOT, we construct ClimateIQA, a novel meteorological visual question answering (VQA) dataset, comprising 26,280 high-resolution heatmaps and 762,120 instruction samples for wind gust, total precipitation, wind chill index and heat index analysis. ClimateIQA enhances VLM training by incorporating spatial cues, geographic metadata, and reanalysis data, improving model accuracy in interpreting and describing extreme weather features. Furthermore, we develop Climate-Zoo, a suite of fine-tuned VLMs based on SPOT-empowered ClimateIQA, which significantly outperforms existing models in meteorological heatmap tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2406_09838
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ClimateIQA: A New Dataset and Benchmark to Advance Vision-Language Models in Meteorology Anomalies Analysis
Chen, Jian
Zhou, Peilin
Hua, Yining
Chong, Dading
Cao, Meng
Li, Yaowei
Chen, Wei
Zhu, Bing
Liang, Junwei
Yuan, Zixuan
Computer Vision and Pattern Recognition
Artificial Intelligence
Meteorological heatmaps play a vital role in deciphering extreme weather phenomena, yet their inherent complexities marked by irregular contours, unstructured patterns, and complex color variations present unique analytical hurdles for state-of-the-art Vision-Language Models (VLMs). Current state-of-the-art models like GPT-4o, Qwen-VL, and LLaVA 1.6 struggle with tasks such as precise color identification and spatial localization, resulting in inaccurate or incomplete interpretations. To address these challenges, we introduce Sparse Position and Outline Tracking (SPOT), a novel algorithm specifically designed to process irregularly shaped colored regions in visual data. SPOT identifies and localizes these regions by extracting their spatial coordinates, enabling structured representations of irregular shapes. Building on SPOT, we construct ClimateIQA, a novel meteorological visual question answering (VQA) dataset, comprising 26,280 high-resolution heatmaps and 762,120 instruction samples for wind gust, total precipitation, wind chill index and heat index analysis. ClimateIQA enhances VLM training by incorporating spatial cues, geographic metadata, and reanalysis data, improving model accuracy in interpreting and describing extreme weather features. Furthermore, we develop Climate-Zoo, a suite of fine-tuned VLMs based on SPOT-empowered ClimateIQA, which significantly outperforms existing models in meteorological heatmap tasks.
title ClimateIQA: A New Dataset and Benchmark to Advance Vision-Language Models in Meteorology Anomalies Analysis
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2406.09838