Benefits of using blended generative adversarial network images to augment classification model training data sets
Benefits of using blended generative adversarial network images to augment classification model training data sets
复制标题
使用混合生成对抗网络图像来增强分类模型训练数据集的好处
DOI：
10.1177/15485129231170225
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Trevor J. Bihl
中科院分区：
文献类型：
--
作者：
Benjamin J. McCloskey;Bruce A Cox;Lance E. Champagne;Trevor J. Bihl
在过去的十年中，目标检测算法已经达到了近乎超人的水平;然而，这些算法需要大量不同的训练数据集，以确保其操作性能与测试期间展示的性能相匹配。这些数据集的收集和人工标记可能是昂贵的，在某些情况下，例如情报，监视和侦察罕见事件，甚至可能不可行。这项研究提出了一种新的方法，通过利用生成对抗网络的多个模型来产生高质量和低质量的车辆合成图像，并将这些图像与真实的车辆图像一起插入到真实的背景中，从而在训练数据集中创建额外的可变性。这项研究表明，与在原始非增强训练集上训练的YOLOv 4-Tiny模型相比，平均绝对百分比误差平均增加了17.90%，平均交叉率平均提高了14.44%。此外，我们的研究增加了一个小的，但越来越多的文献表明，将低质量的图像纳入训练数据集有利于计算机视觉模型的性能。
Object detection algorithms have reached nearly superhuman levels within the last decade; however, these algorithms require large diverse training data sets to ensure their operational performance matches performance demonstrated during testing. The collection and human labeling of such data sets can be expensive and, in some cases, such as Intelligence, Surveillance and Reconnaissance of rare events it may not even be feasible. This research proposes a novel method for creating additional variability within the training data set by utilizing multiple models of generative adversarial networks producing both high- and low-quality synthetic images of vehicles and inserting those images alongside images of real vehicles into real backgrounds. This research demonstrates a 17.90% increase in mean absolute percentage error, on average, compared to the YOLOv4-Tiny Model trained on the original non-augmented training set as well as a 14.44% average improvement in the average intersection over union rate. In addition, our research adds to a small, but growing, body of literature indicating that the inclusion of low-quality images into training data sets is beneficial to the performance of computer vision models.