论文标题
IDA：应用于显着对象检测的改进数据增加
IDA: Improved Data Augmentation Applied to Salient Object Detection
论文作者
论文摘要
在本文中，我们提出了一项改进的数据增强（IDA）技术，该技术的重点是显着对象检测（SOD）。文献中提出的标准数据增强技术，例如图像裁剪，旋转，翻转和调整大小，仅产生现有示例的变化，从而提供有限的概括。我们的方法结合了图像介绍，仿射转换以及不同生成的背景图像的线性组合以及从标记数据中提取的显着对象。我们提出的技术可以在保留背景信息的同时更精确地控制对象的位置和大小。背景选择基于图像间优化，而对象大小则遵循指定间隔内均匀的随机分布，并且对象位置是最佳的图像内图像。我们表明，在SOD字段的几个著名数据集上，我们的方法用于培训最先进的神经网络时，我们的方法可以提高细分质量。将我们的方法与其他方法相结合，超过了传统技术，例如F-Measure的水平叶片为0.52％，精度为1.19％。我们还在7个不同的SOD数据集中提供了评估，具有9个不同的评估指标和评估方法的平均排名。
In this paper, we present an Improved Data Augmentation (IDA) technique focused on Salient Object Detection (SOD). Standard data augmentation techniques proposed in the literature, such as image cropping, rotation, flipping, and resizing, only generate variations of the existing examples, providing a limited generalization. Our method combines image inpainting, affine transformations, and the linear combination of different generated background images with salient objects extracted from labeled data. Our proposed technique enables more precise control of the object's position and size while preserving background information. The background choice is based on an inter-image optimization, while object size follows a uniform random distribution within a specified interval, and the object position is intra-image optimal. We show that our method improves the segmentation quality when used for training state-of-the-art neural networks on several famous datasets of the SOD field. Combining our method with others surpasses traditional techniques such as horizontal-flip in 0.52% for F-measure and 1.19% for Precision. We also provide an evaluation in 7 different SOD datasets, with 9 distinct evaluation metrics and an average ranking of the evaluated methods.
