Abstract Scientific studies on species identification in fish have considerable significance in aquatic ecosystems and quality evaluation. The morphological differences between different fish species are obvious. Machine learning methods use artificial prior knowledge to extract fish features, which is time-consuming, laborious, and subjective. Recently, deep learning-based identification of fish species has been widely used. However, fish species identification still faces many challenges due to the small scale of fish samples and the imbalance of the number of categories. For example, the model is prone to being overfitted, and the performance of the classifier is biased to the fish species of most samples. To solve the above problems, this paper proposes a fish species identification approach based on SE-ResNet152 and class-balanced focal loss. First, visualization analysis and image preprocessing of fish datasets are carried out. Second, the SE-ResNet152 model is constructed as a generalized feature extractor and is migrated to the target dataset. Finally, we apply the class-balanced focal loss function to train the SE-ResNet152 model, and realize fish species identification on three fish image views (body, head, and scale). The proposed method was tested on the Fish-Pak public dataset and achieved 98.80%, 96.67%, and 91.25% accuracy on the three fish image views, respectively. To ensure the superior performance of the proposed method, we performed an experimental comparison with other methods involving SENet154, DenseNet121, ResNet18, ResNet152, VGG16, cross-entropy, and focal loss. Comprehensive empirical analyses reveal that the proposed method achieves good performance on the three fish image views and outperforms common methods.

中文翻译：

---

基于迁移学习和 SE-ResNet152 网络的小规模不平衡鱼类物种识别

摘要 鱼类物种鉴定的科学研究在水生生态系统和质量评价中具有重要意义。不同鱼类之间的形态差异很明显。机器学习方法使用人工先验知识来提取鱼类特征，耗时、费力且主观。最近，基于深度学习的鱼类物种识别已被广泛使用。然而，由于鱼类样本规模小、类别数量不平衡，鱼类物种鉴定仍面临诸多挑战。例如，模型容易过拟合，分类器的性能偏向于大多数样本的鱼种。针对上述问题，本文提出了一种基于SE-ResNet152和class-balanced focus loss的鱼类物种识别方法。首先，对鱼类数据集进行可视化分析和图像预处理。其次，将 SE-ResNet152 模型构建为广义特征提取器并迁移到目标数据集。最后，我们应用类平衡的焦点损失函数来训练 SE-ResNet152 模型，并在三个鱼类图像视图（身体、头部和尺度）上实现鱼类物种识别。所提出的方法在 Fish-Pak 公共数据集上进行了测试，在三种鱼类图像视图上分别达到了 98.80%、96.67% 和 91.25% 的准确率。为了确保所提出方法的优越性能，我们与其他方法进行了实验比较，包括 SENet154、DenseNet121、ResNet18、ResNet152、VGG16、交叉熵和焦点损失。