Identification of fossil species is crucial to evolutionary studies. Recent advances from deep learning have shown promising prospects in fossil image identification. However, the quantity and quality of labeled fossil images are often limited due to fossil preservation, conditioned sampling, and expensive and inconsistent label annotation by domain experts, which pose great challenges to training deep learning based image classification models. To address these challenges, we follow the idea of the wisdom of crowds and propose a multiview ensemble framework, which collects Original (O), Gray (G), and Skeleton (S) views of each fossil image reflecting its different characteristics to train multiple base models, and then makes the final decision via soft voting. Experiments on the largest fusulinid dataset with 2400 images show that the proposed OGS consistently outperforms baselines (using a single model for each view), and obtains superior or comparable performance compared to OOO (using three base models for three the same Original views). While considering the identification consistency estimation with respect to human experts, OGS receives the highest agreement with the original labels of dataset and with the re-identifications of two human experts. We conclude that the proposed framework can present state-of-the-art performance in the fusulinid fossil identification case study. This framework is designed for general fossil identification and it is expected to see applications to other fossil datasets in future work. Notably, the result, which shows more performance gains as train set size decreases or over a smaller imbalance fossil dataset, suggests the potential application to identify rare fossil images. The proposed framework also demonstrates its potential for assessing and resolving inconsistencies in fossil identification.

翻译：化石物种鉴定对于进化研究至关重要。近年来，深度学习在化石图像识别领域展现出显著前景。然而，由于化石保存状况、条件性采样以及领域专家标注昂贵且不一致等因素，标记化石图像的数量与质量往往受限，这对基于深度学习的图像分类模型训练构成重大挑战。为解决这些问题，我们遵循"群体智慧"思想，提出一种多视图集成框架，该框架通过采集每张化石图像的原始（Original, O）、灰度（Gray, G）与骨骼（Skeleton, S）视图（分别反映图像不同特征）来训练多个基模型，并通过软投票机制做出最终决策。在包含2400张图像的最大型䗴类化石数据集上的实验表明，所提出的OGS方法始终优于基线方法（针对每个视图使用单一模型），并且与OOO方法（对三个相同原始视图使用三个基模型）相比表现出优越或相当的性能。在与人类专家的鉴定一致性评估中，OGS与数据集原始标签及两位人类专家重新鉴定结果的一致性最高。我们得出结论：该框架在䗴类化石鉴定案例研究中达到了当前最优性能。该框架专为通用化石鉴定设计，预计未来可应用于其他化石数据集。值得注意的是，随着训练集规模减小或在不平衡性较小的化石数据集上，该框架展现出更强的性能增益，这预示着其在稀有化石图像识别中的潜在应用价值。此外，该框架还展示了评估与解决化石鉴定不一致性的潜力。