论文标题
通过添加最终批准层：一项实证研究，提高模型的准确性不平衡图像分类任务
Improving Model Accuracy for Imbalanced Image Classification Tasks by Adding a Final Batch Normalization Layer: An Empirical Study
论文作者
论文摘要
一些现实的领域，例如农业和医疗保健，构成了记录构成罕见事件的早期疾病适应症，但在该阶段的精确检测至关重要。在涵盖复杂特征的高度不平衡的分类问题中，深度学习（DL）非常需要，因为它具有强大的检测能力。同时，在实践中观察到DL是为了支持多数族裔，而不是少数族裔阶层，因此遭受了对目标早期适应症的检测不准确。为了模拟这种情况，我们人为地为某些植物类型从Plantvillage数据集中人为地产生偏度（99％vs. 1％），以作为通过转移学习对稀缺视觉提示分类的基础。通过从某些植物类型中随机和不均匀挑选健康和不健康的样本以形成训练集，我们将基本实验视为微调Resnet34和VGG19体系结构，然后在健康和不健康图像的平衡数据集中测试模型性能。我们从经验上观察到，在VGG19中输出层之前，在添加最终批准归一层（BN）层时，初始F1测试分数在少数族裔类别中的最初F1测试分数从0.29跃升至0.95。我们证明，在现代CNN体系结构中的输出层在最小化训练时间和测试少数类别中的少数群体中，在高度不平衡的数据集中，使用额外的BN层具有相当大的影响。此外，当使用最终的BN时，最大程度地减少损失功能可能不是确保在此类问题中为少数族裔级别的高F1测试得分的最佳方法。也就是说，即使网络在做出预测时不够自信，该网络也可能会更好。导致另一个关于为什么SoftMax输出的讨论不是DL模型的良好不确定性度量。
Some real-world domains, such as Agriculture and Healthcare, comprise early-stage disease indications whose recording constitutes a rare event, and yet, whose precise detection at that stage is critical. In this type of highly imbalanced classification problems, which encompass complex features, deep learning (DL) is much needed because of its strong detection capabilities. At the same time, DL is observed in practice to favor majority over minority classes and consequently suffer from inaccurate detection of the targeted early-stage indications. To simulate such scenarios, we artificially generate skewness (99% vs. 1%) for certain plant types out of the PlantVillage dataset as a basis for classification of scarce visual cues through transfer learning. By randomly and unevenly picking healthy and unhealthy samples from certain plant types to form a training set, we consider a base experiment as fine-tuning ResNet34 and VGG19 architectures and then testing the model performance on a balanced dataset of healthy and unhealthy images. We empirically observe that the initial F1 test score jumps from 0.29 to 0.95 for the minority class upon adding a final Batch Normalization (BN) layer just before the output layer in VGG19. We demonstrate that utilizing an additional BN layer before the output layer in modern CNN architectures has a considerable impact in terms of minimizing the training time and testing error for minority classes in highly imbalanced data sets. Moreover, when the final BN is employed, minimizing the loss function may not be the best way to assure a high F1 test score for minority classes in such problems. That is, the network might perform better even if it is not confident enough while making a prediction; leading to another discussion about why softmax output is not a good uncertainty measure for DL models.
