Towards Analysis-friendly Face Representation with Scalable Feature and Texture Compression
release_ijgozsonkjbtjd6q6cjgxuugc4
by
Shurun Wang, Shiqi Wang, Wenhan Yang, Xinfeng Zhang, Shanshe Wang, Siwei Ma, Wen Gao
2020
Abstract
It plays a fundamental role to compactly represent the visual information
towards the optimization of the ultimate utility in myriad visual data centered
applications. With numerous approaches proposed to efficiently compress the
texture and visual features serving human visual perception and machine
intelligence respectively, much less work has been dedicated to studying the
interactions between them. Here we investigate the integration of feature and
texture compression, and show that a universal and collaborative visual
information representation can be achieved in a hierarchical way. In
particular, we study the feature and texture compression in a scalable coding
framework, where the base layer serves as the deep learning feature and
enhancement layer targets to perfectly reconstruct the texture. Based on the
strong generative capability of deep neural networks, the gap between the base
feature layer and enhancement layer is further filled with the feature level
texture reconstruction, aiming to further construct texture representation from
feature. As such, the residuals between the original and reconstructed texture
could be further conveyed in the enhancement layer. To improve the efficiency
of the proposed framework, the base layer neural network is trained in a
multi-task manner such that the learned features enjoy both high quality
reconstruction and high accuracy analysis. We further demonstrate the framework
and optimization strategies in face image compression, and promising coding
performance has been achieved in terms of both rate-fidelity and rate-accuracy.
In text/plain
format
Archived Files and Locations
application/pdf 8.9 MB
file_hkoaeue5ynfbhef563cpbkqfmy
|
arxiv.org (repository) web.archive.org (webarchive) |
2004.10043v1
access all versions, variants, and formats of this works (eg, pre-prints)