An Importance Aware Weighted Coding Theorem Using Message Importance Measure

Zhu, Zheqi; Liu, Shanyun; Sheng, Rui; Wan, Shuo; Fan, Pingyi; Letaief, Khaled B.

doi:10.1109/lcomm.2020.2992048

Cited by 4 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The conditional message importance measure (CMIM) is given by Definition 3 The message importance loss based on MIM and CMIM is given by MIM loss has been used in several fields such as information compression, distribution estimation, anomaly detection, recommendation, and IoT 11,17 . The parameter in MIM can be selected to amplify the weights of certain elements according to the user's preference 18 . In Sect.…”

Section: Definitionmentioning

confidence: 99%

Robust, practical and comprehensive analysis of soft compression image coding algorithms for big data

Xin

Fan

2023

Sci Rep

Self Cite

View full text Add to dashboard Cite

With the advancement of intelligent vision algorithms and devices, image reprocessing and secondary propagation are becoming increasingly prevalent. A large number of similar images are being produced rapidly and widely, resulting in the homogeneity and similarity of images. Moreover, it brings new challenges to compression systems, which need to exploit the potential of deep features and side information of images. However, traditional methods are incompetent for this issue. Soft compression is a novel data-driven image coding algorithm with superior performance. Compared with existing paradigms, it has distinctive characteristics: from hard to soft, from pixels to shapes, and from fixed to random. Soft compression may hold promise for human-centric/data-centric intelligent systems, making them efficient and reliable and finding potential in the metaverse and digital twins, etc. In this paper, we present a comprehensive and practical analysis of soft compression, revealing the functional role of each component in the system.

show abstract

Section: Definitionmentioning

confidence: 99%

Robust, practical and comprehensive analysis of soft compression image coding algorithms for big data

Xin

Fan

2023

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…MIM loss has been used in several fields such as information compression, distribution estimation, anomaly detection, recommendation and IoT [11,17] . The parameter in MIM can be selected to amplify the weights of certain elements according to user's preference [18]. In Section 2, we will use shannon mutual information, α-mutual information and MIM loss to measure the mutual information between different components of an image.…”

Section: Definitionmentioning

confidence: 99%

Robust, practical and comprehensive analysis of soft compression image coding algorithms for big data

Xin

Fan

2022

Preprint

Self Cite

View full text Add to dashboard Cite

With the advancement of intelligent vision algorithms and devices, image reprocessing and secondary propagation are becoming increasingly prevalent. A large number of similar images are being produced rapidly and widely, resulting in the homogeneity and similarity of images. Moreover, it brings new challenges to compression systems, which need to exploit the potential of deep features and side information of images. However, traditional methods are incompetent for this issue. Soft compression is a novel data-driven image coding algorithm with superior performance. Compared with existing paradigms, it has distinctive characteristics: from hard to soft, from pixels to shapes, and from fixed to random. Soft compression may hold promise for human-centric/data-centric intelligent systems, making them efficient and reliable and finding potential in metaverse and digital twins, etc. In this paper, we present a comprehensive and practical analysis of soft compression, revealing the functional role of each component in the system.

show abstract