arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.05889cs.CV
收藏

评估低水平视力任务的COPY-BLEND增强

Evaluating COPY-BLEND Augmentation for Low Level Vision Tasks

KAIST(韩国科学技术院);University of Copenhagen(哥本哈根大学)

Pranjay Shyam, Sandeep Singh Sengar, Kuk-Jin Yoon, Kyung-Soo Kim

摘要:

基于区域修改的数据增强技术已被证明可以提高高级视觉任务(目标检测、语义分割、图像分类等)的性能。通过鼓励底层算法专注于多个区别特征。然而,由于这些技术破坏了与相邻区域的空间关系,因此当使用它们来训练为低水平视觉任务(低光图像增强、图像去雾、去模糊等)设计的算法时,性能可能恶化。其中恢复区域及其相邻区域之间的纹理一致性对于确保有效性能是重要的。在本文中,我们研究了一个简单的复制混合数据增强技术,复制补丁从嘈杂的图像和混合到一个干净的图像,反之亦然,以确保底层算法本地化和恢复受影响的地区,从而提高感知质量的恢复图像的功效。为了评估性能改进,我们与不同的基于区域修改的增强技术一起进行了广泛的实验,并报告了一些观察结果,例如性能提高,对训练数据集的要求降低,以及在不对基线算法进行任何修改的情况下,在低光图像增强,图像去雾和图像去模糊等任务中的早期收敛。

英文摘要:

Region modification-based data augmentation techniques have shown to improve performance for high level vision tasks (object detection, semantic segmentation, image classification, etc.) by encouraging underlying algorithms to focus on multiple discriminative features. However, as these techniques destroy spatial relationship with neighboring regions, performance can be deteriorated when using them to train algorithms designed for low level vision tasks (low light image enhancement, image dehazing, deblurring, etc.) where textural consistency between recovered and its neighboring regions is important to ensure effective performance. In this paper, we examine the efficacy of a simple copy-blend data augmentation technique that copies patches from noisy images and blends onto a clean image and vice versa to ensure that an underlying algorithm localizes and recovers affected regions resulting in increased perceptual quality of a recovered image. To assess performance improvement, we perform extensive experiments alongside different region modification-based augmentation techniques and report observations such as improved performance, reduced requirement for training dataset, and early convergence across tasks such as low light image enhancement, image dehazing and image deblurring without any modification to baseline algorithm.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑