# Revisit Visual Representation in Analytics Taxonomy: A Compression Perspective

arXiv: https://arxiv.org/abs/2106.08512 · HTML: https://mlsanity.com/paper/2106.08512/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 30 references that are in the map.
- First posted on arXiv 16 Jun 2021.

## Builds on (most cited first, 15 of 15)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018)
- [Deep Learning and the Information Bottleneck Principle](https://mlsanity.com/paper/1503.02406/) (2015)
- [Taskonomy: Disentangling Task Transfer Learning](https://mlsanity.com/paper/1804.08328/) (2018)
- [Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture](https://mlsanity.com/paper/1411.4734/) (2014)
- [Video Coding for Machines: A Paradigm of Collaborative Compression and Intelligent Analytics](https://mlsanity.com/paper/2001.03569/) (2020)
- [Fast Edge Detection Using Structured Forests](https://mlsanity.com/paper/1406.5549/) (2014)
- [Towards Image Understanding from Deep Compression without Decoding](https://mlsanity.com/paper/1803.06131/) (2018)
- [End-to-end Learning of Compressible Features](https://mlsanity.com/paper/2007.11797/) (2020)
- [End-to-end optimized image compression for machines, a study](https://mlsanity.com/paper/2011.06409/) (2020)
- [High efficiency compression for object detection](https://mlsanity.com/paper/1710.11151/) (2017)
- [Compact Descriptors for Video Analysis: the Emerging MPEG Standard](https://mlsanity.com/paper/1704.08141/) (2017)
- [Lightweight compression of neural network feature tensors for collaborative intelligence](https://mlsanity.com/paper/2105.06002/) (2021)
- [An Emerging Coding Paradigm VCM: A Scalable Coding Approach Beyond Feature and Signal](https://mlsanity.com/paper/2001.03004/) (2020)

## Built on by (most cited first, 1 of 1)

- [A New Image Codec Paradigm for Human and Machine Uses](https://mlsanity.com/paper/2112.10071/) (2021)

## Abstract (arXiv)

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.