论文标题
深度学习中的分析和减轻JPEG压缩缺陷
Analyzing and Mitigating JPEG Compression Defects in Deep Learning
论文作者
论文摘要
随着深度学习方法的扩散，在消费者环境中，许多被认为学术的计算机视觉问题是可行的。消费者应用程序的一个缺点是有损压缩，从工程的角度来看，这是有效，便宜地存储和传输用户图像所必需的。尽管如此，几乎没有研究压缩对深神经网络和基准数据集的影响，通常以高质量的方式无损地压缩或压缩。在这里，我们介绍了JPEG压缩对一系列常见任务和数据集的影响的统一研究。我们表明，对高压的共同绩效指标受到重大惩罚。我们测试了减轻这种惩罚的几种方法，包括一种基于伪像校正的新方法，不需要标签才能训练。
With the proliferation of deep learning methods, many computer vision problems which were considered academic are now viable in the consumer setting. One drawback of consumer applications is lossy compression, which is necessary from an engineering standpoint to efficiently and cheaply store and transmit user images. Despite this, there has been little study of the effect of compression on deep neural networks and benchmark datasets are often losslessly compressed or compressed at high quality. Here we present a unified study of the effects of JPEG compression on a range of common tasks and datasets. We show that there is a significant penalty on common performance metrics for high compression. We test several methods for mitigating this penalty, including a novel method based on artifact correction which requires no labels to train.
