Can I read Adaptive Compression for Online Computer Vision: An Edge Reinforcement Learning Approach on EtoBox?

Adaptive Compression for Online Computer Vision: An Edge Reinforcement Learning Approach by Zhaoliang He; Hongshan Li; Zhi Wang; Shutao Xia; Wenwu Zhu is a Computer Science article available to read on EtoBox.

What is Adaptive Compression for Online Computer Vision: An Edge Reinforcement Learning Approach about?

With the growth of computer vision-based applications, an explosive amount of images have been uploaded to cloud servers that host such online computer vision algorithms, usually in the form of deep learning models. JPEG has been used as the de facto compression and encapsulation method for images. However, standard JPEG configuration does not always perform well for compressing images that are to be processed by a deep learning model—for example, the standard quality level of JPEG leads to 50% of size overhead (compared with the best quality level selection) on ImageNet under the same inference accuracy in popular computer vision models (e.g., InceptionNet and ResNet). Knowing this, designing a better JPEG configuration for online computer vision-based services is still extremely challenging. First, cloud-based computer vision models are usually a black box to end-users; thus, it is challenging to design JPEG configuration without knowing their model structures. Second, the “optimal” JPEG configuration is not fixed; instead, it is determined by confounding factors, including the characteristics of the input images and the model, the expected accuracy and image size, and so forth.

Who reads Adaptive Compression for Online Computer Vision: An Edge Reinforcement Learning Approach?

Author

Zhaoliang He; Hongshan Li; Zhi Wang; Shutao Xia; Wenwu Zhu

Publisher

ACM

Published

2021

Language

EN

Field

Computer Science (Physical Sciences)