DeepSIC: Deep Semantic Image Compression

TL;DR

DeepSIC introduces two innovative architectures for image compression that embed semantic information during encoding or decoding, reducing redundant analysis and enabling semantic-aware image storage and transmission.

Contribution

The paper proposes two novel architectures for semantic image compression that integrate semantic analysis into the compression process, enhancing efficiency and semantic preservation.

Findings

Achieved promising results on benchmarking datasets.

Shared feature maps improve compression and semantic analysis integration.

Analyzed advantages and disadvantages of the proposed methods.

Abstract

Incorporating semantic information into the codecs during image compression can significantly reduce the repetitive computation of fundamental semantic analysis (such as object recognition) in client-side applications. The same practice also enable the compressed code to carry the image semantic information during storage and transmission. In this paper, we propose a concept called Deep Semantic Image Compression (DeepSIC) and put forward two novel architectures that aim to reconstruct the compressed image and generate corresponding semantic representations at the same time. The first architecture performs semantic analysis in the encoding process by reserving a portion of the bits from the compressed code to store the semantic representations. The second performs semantic analysis in the decoding step with the feature maps that are embedded in the compressed code. In both architectures, the feature maps are shared by the compression and the semantic analytics modules. To validate our approaches, we conduct experiments on the publicly available benchmarking datasets and achieve promising results. We also provide a thorough analysis of the advantages and disadvantages of the proposed technique.