Side Information Driven Image Coding for Machines
Side Information Driven Image Coding for Machines
复制标题
DOI：
10.1109/pcs56426.2022.10018039
复制
发表时间：
2022-12
期刊：
影响因子：
--
通讯作者：
Zhongpeng Zhang;Y. Liu
中科院分区：
文献类型：
--
作者：
Zhongpeng Zhang;Y. Liu
随着计算机视觉技术的不断提高，越来越多的图像信息由机器而不是人类消费。机器图像编码（ICM）是对图像数据进行压缩，以便更有效地发送到接收器端，供机器进行视觉分析。典型的基于深度学习的ICM结构包含一个通过互联网压缩和传输图像的编解码器网络和一个语义分析任务网络，如图像分类和对象识别。在编解码器部分中，边信息是用于压缩图像潜表示的超先验或超先验的分层。本文提出了一种基于深度学习的边信息驱动图像编码（SIIC）框架。它只压缩和发送侧信息到接收器的图像分类任务。我们在每像素0.046位的ImageNet 1K数据集上获得了70.38%的前1精度。
With the continuous improvement of computer vision technology, more and more image information is consumed by machines rather than humans. Image coding for machines (ICM) is to compress image data such that they can be more efficiently sent to the receiver side for machines to conduct visual analysis. A typical deep learning-based ICM structure contains one codec network which compresses and transmits images through the Internet and one semantic analysis task network such as image classification and object recognition. In the codec part, the side information is the hyper-prior or hierarchical layers of hyper-priors for the compression of image latent representations. In this paper, we propose a Side Information Driven Image Coding (SIIC) framework based on deep learning. It only compresses and transmits the side information to the receiver for image classification tasks. We obtain a top-l accuracy of 70.38% on the ImageNet1K dataset with 0.046 bits per pixel.