Revisit Visual Representation in Analytics Taxonomy: A Compression Perspective

by   Yueyu Hu, et al.

Visual analytics have played an increasingly critical role in the Internet of Things, where massive visual signals have to be compressed and fed into machines. But facing such big data and constrained bandwidth capacity, existing image/video compression methods lead to very low-quality representations, while existing feature compression techniques fail to support diversified visual analytics applications/tasks with low-bit-rate representations. In this paper, we raise and study the novel problem of supporting multiple machine vision analytics tasks with the compressed visual representation, namely, the information compression problem in analytics taxonomy. By utilizing the intrinsic transferability among different tasks, our framework successfully constructs compact and expressive representations at low bit-rates to support a diversified set of machine vision tasks, including both high-level semantic-related tasks and mid-level geometry analytic tasks. In order to impose compactness in the representations, we propose a codebook-based hyperprior, which helps map the representation into a low-dimensional manifold. As it well fits the signal structure of the deep visual feature, it facilitates more accurate entropy estimation, and results in higher compression efficiency. With the proposed framework and the codebook-based hyperprior, we further investigate the relationship of different task features owning different levels of abstraction granularity. Experimental results demonstrate that with the proposed scheme, a set of diversified tasks can be supported at a significantly lower bit-rate, compared with existing compression schemes.


page 1

page 2

page 3

page 4


Video Coding for Machine: Compact Visual Representation Compression for Intelligent Collaborative Analytics

Video Coding for Machines (VCM) is committed to bridging to an extent se...

DeepVA: Bridging Cognition and Computation through Semantic Interaction and Deep Learning

This paper examines how deep learning (DL) representations, in contrast ...

End-to-end Compression Towards Machine Vision: Network Architecture Design and Optimization

The visual signal compression is a long-standing problem. Fueled by the ...

GreedyGD: Enhanced Generalized Deduplication for Direct Analytics in IoT

Exponential growth in the amount of data generated by the Internet of Th...

Conceptual Compression via Deep Structure and Texture Synthesis

Existing compression methods typically focus on the removal of signal-le...

Thousand to One: Semantic Prior Modeling for Conceptual Coding

Conceptual coding has been an emerging research topic recently, which en...

A New Image Codec Paradigm for Human and Machine Uses

With the AI of Things (AIoT) development, a huge amount of visual data, ...

Please sign up or login with your details

Forgot password? Click here to reset