野外多模态病害识别的基准评测与通用基线
Benchmarking In-the-wild Multimodal Disease Recognition and A Versatile Baseline
AI总结：
针对野外植物病害图像类间差异小、类内方差大的问题，本文提出一个包含最多病害类别及文本描述的野外多模态数据集，并设计基于多原型的通用基线，在分类、少样本和无训练场景下均表现有效。
摘要：
现有植物病害分类模型在识别实验室拍摄的病害图像方面已取得显著性能，但它们在分类野外图像时性能往往大幅下降。此外，我们观察到野外植物图像在不同病害之间可能呈现相似外观（即类间差异小），而同一种病害可能看起来差异很大（即类内方差大）。受这一观察启发，我们提出了一个野外多模态植物病害识别数据集，该数据集包含数量最多的病害类别，并为每种病害提供基于文本的描述。特别地，新提供的文本描述旨在提供丰富的文本模态信息，并有助于解决类间差异小和类内方差大的野外病害分类问题。因此，我们提出的数据集可被视为评估现实世界中病害识别方法的理想测试平台。此外，我们进一步提出一个强大且通用的基线模型，该模型通过给定类别的多个原型对文本描述和视觉数据进行建模。通过在分类中融合多模态原型的贡献，我们的基线能够有效解决类间差异小和类内方差大的问题。值得注意的是，我们的基线模型不仅可以对病害进行分类，还能够在少样本或无训练场景下识别病害。大量基准评测结果表明，我们提出的野外多模态数据集为植物病害识别任务带来了许多新挑战，未来工作仍有很大提升空间。
英文摘要：
Existing plant disease classification models have achieved remarkable performance in recognizing in-laboratory diseased images. However, their performance often significantly degrades in classifying in-the-wild images. Furthermore, we observed that in-the-wild plant images may exhibit similar appearances across various diseases (i.e., small inter-class discrepancy) while the same diseases may look quite different (i.e., large intra-class variance). Motivated by this observation, we propose an in-the-wild multimodal plant disease recognition dataset that contains the largest number of disease classes but also text-based descriptions for each disease. Particularly, the newly provided text descriptions are introduced to provide rich information in textual modality and facilitate in-the-wild disease classification with small inter-class discrepancy and large intra-class variance issues. Therefore, our proposed dataset can be regarded as an ideal testbed for evaluating disease recognition methods in the real world. In addition, we further present a strong yet versatile baseline that models text descriptions and visual data through multiple prototypes for a given class. By fusing the contributions of multimodal prototypes in classification, our baseline can effectively address the small inter-class discrepancy and large intra-class variance issues. Remarkably, our baseline model can not only classify diseases but also recognize diseases in few-shot or training-free scenarios. Extensive benchmarking results demonstrate that our proposed in-the-wild multimodal dataset sets many new challenges to the plant disease recognition task and there is a large space to improve for future works.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
