{"title":"识别前三思:用于一般精细交通标志识别的大型多模态模型","authors":"Yaozong Gan, Guang Li, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama","doi":"arxiv-2409.01534","DOIUrl":null,"url":null,"abstract":"We propose a new strategy called think twice before recognizing to improve\nfine-grained traffic sign recognition (TSR). Fine-grained TSR in the wild is\ndifficult due to the complex road conditions, and existing approaches\nparticularly struggle with cross-country TSR when data is lacking. Our strategy\nachieves effective fine-grained TSR by stimulating the multiple-thinking\ncapability of large multimodal models (LMM). We introduce context,\ncharacteristic, and differential descriptions to design multiple thinking\nprocesses for the LMM. The context descriptions with center coordinate prompt\noptimization help the LMM to locate the target traffic sign in the original\nroad images containing multiple traffic signs and filter irrelevant answers\nthrough the proposed prior traffic sign hypothesis. The characteristic\ndescription is based on few-shot in-context learning of template traffic signs,\nwhich decreases the cross-domain difference and enhances the fine-grained\nrecognition capability of the LMM. The differential descriptions of similar\ntraffic signs optimize the multimodal thinking capability of the LMM. The\nproposed method is independent of training data and requires only simple and\nuniform instructions. We conducted extensive experiments on three benchmark\ndatasets and two real-world datasets from different countries, and the proposed\nmethod achieves state-of-the-art TSR results on all five datasets.","PeriodicalId":501480,"journal":{"name":"arXiv - CS - Multimedia","volume":"34 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Think Twice Before Recognizing: Large Multimodal Models for General Fine-grained Traffic Sign Recognition\",\"authors\":\"Yaozong Gan, Guang Li, Ren Togo, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama\",\"doi\":\"arxiv-2409.01534\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We propose a new strategy called think twice before recognizing to improve\\nfine-grained traffic sign recognition (TSR). Fine-grained TSR in the wild is\\ndifficult due to the complex road conditions, and existing approaches\\nparticularly struggle with cross-country TSR when data is lacking. Our strategy\\nachieves effective fine-grained TSR by stimulating the multiple-thinking\\ncapability of large multimodal models (LMM). We introduce context,\\ncharacteristic, and differential descriptions to design multiple thinking\\nprocesses for the LMM. The context descriptions with center coordinate prompt\\noptimization help the LMM to locate the target traffic sign in the original\\nroad images containing multiple traffic signs and filter irrelevant answers\\nthrough the proposed prior traffic sign hypothesis. The characteristic\\ndescription is based on few-shot in-context learning of template traffic signs,\\nwhich decreases the cross-domain difference and enhances the fine-grained\\nrecognition capability of the LMM. The differential descriptions of similar\\ntraffic signs optimize the multimodal thinking capability of the LMM. The\\nproposed method is independent of training data and requires only simple and\\nuniform instructions. We conducted extensive experiments on three benchmark\\ndatasets and two real-world datasets from different countries, and the proposed\\nmethod achieves state-of-the-art TSR results on all five datasets.\",\"PeriodicalId\":501480,\"journal\":{\"name\":\"arXiv - CS - Multimedia\",\"volume\":\"34 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Multimedia\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.01534\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Multimedia","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.01534","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
摘要
我们提出了一种名为 "三思而后行 "的新策略,以改进细粒度交通标志识别(TSR)。由于路况复杂,在野外进行细粒度 TSR 十分困难,现有方法尤其难以在缺乏数据的情况下进行跨国 TSR。我们的策略通过激发大型多模态模型(LMM)的多重思维能力来实现有效的细粒度 TSR。我们引入了上下文、特征和差异描述来为 LMM 设计多重思维过程。带有中心坐标提示优化的上下文描述有助于 LMM 在包含多个交通标志的原始道路图像中定位目标交通标志,并通过提出的先验交通标志假设过滤无关答案。特征描述是基于对模板交通标志的少帧上下文学习,从而减小了跨域差异,增强了 LMM 的细粒度识别能力。对相似交通标志的差分描述优化了 LMM 的多模态思维能力。所提出的方法与训练数据无关,只需要简单而统一的指令。我们在三个基准数据集和两个来自不同国家的实际数据集上进行了广泛的实验,所提出的方法在所有五个数据集上都取得了最先进的 TSR 结果。
Think Twice Before Recognizing: Large Multimodal Models for General Fine-grained Traffic Sign Recognition
We propose a new strategy called think twice before recognizing to improve
fine-grained traffic sign recognition (TSR). Fine-grained TSR in the wild is
difficult due to the complex road conditions, and existing approaches
particularly struggle with cross-country TSR when data is lacking. Our strategy
achieves effective fine-grained TSR by stimulating the multiple-thinking
capability of large multimodal models (LMM). We introduce context,
characteristic, and differential descriptions to design multiple thinking
processes for the LMM. The context descriptions with center coordinate prompt
optimization help the LMM to locate the target traffic sign in the original
road images containing multiple traffic signs and filter irrelevant answers
through the proposed prior traffic sign hypothesis. The characteristic
description is based on few-shot in-context learning of template traffic signs,
which decreases the cross-domain difference and enhances the fine-grained
recognition capability of the LMM. The differential descriptions of similar
traffic signs optimize the multimodal thinking capability of the LMM. The
proposed method is independent of training data and requires only simple and
uniform instructions. We conducted extensive experiments on three benchmark
datasets and two real-world datasets from different countries, and the proposed
method achieves state-of-the-art TSR results on all five datasets.