EUVIMEDEUVIMED entdecken
Crossref

Multiscale Feature Importance-Based Bit Allocation for End-to-End Feature Coding for Machines

Junle Liu, Yun Zhang, Zixi Guo, Xiaoxia Huang, Gangyi Jiang

ACM Transactions on Multimedia Computing, Communications, and Applications · 30.09.2025 · 21 (9) · 1-19

DOI: 10.1145/3748654 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 10.09.2025. Verfasst von Junle Liu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 45 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Shenzhen Natural Science Foundation, Shenzhen Key Science and Technology Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Feature Coding for Machines (FCM) aims to compress intermediate features effectively for remote intelligent analytics, which is crucial for future intelligent visual applications. In this article, we propose a Multiscale Feature Importance-based Bit Allocation (MFIBA) for end-to-end FCM. First, we find that the importance of features for machine vision tasks varies with the scales, object size, and image instances. Based on this finding, we propose a Multiscale Feature Importance Prediction (MFIP) module to predict the importance weight for each scale of features. Second, we propose a task loss-rate model to establish the relationship between the task accuracy losses of using compressed features and the bit rate of encoding these features. Finally, we develop an MFIBA for end-to-end FCM, which is able to assign coding bits of multiscale features more reasonably based on their importance. Experimental results demonstrate that when combined with a retained Efficient Learned Image Compression (ELIC), the proposed MFIBA achieves an average of 38.202% bit-rate savings in object detection compared to the anchor ELIC. Moreover, the proposed MFIBA achieves an average of 17.212% and 36.492% feature bit-rate savings for instance segmentation and keypoint detection, respectively. When the proposed MFIBA is applied to the LIC-TCM, it achieves an average of 18.103%, 19.866%, and 19.597% bit-rate savings on three machine vision tasks, respectively, which validates the proposed MFIBA has good generalizability and adaptability to different machine vision tasks and FCM base codecs.

Förderung

  • National Natural Science Foundation of China
  • Shenzhen Natural Science Foundation
  • Shenzhen Key Science and Technology Program
  • Shenzhen-Hong Kong Collaborative Project

Zitieren

APA

Liu, J., Zhang, Y., Guo, Z., Huang, X., & Jiang, G. (2025). Multiscale Feature Importance-Based Bit Allocation for End-to-End Feature Coding for Machines. ACM Transactions on Multimedia Computing, Communications, and Applications, 21(9), 1-19. https://doi.org/10.1145/3748654

Vancouver

Liu J, Zhang Y, Guo Z, Huang X, Jiang G. Multiscale Feature Importance-Based Bit Allocation for End-to-End Feature Coding for Machines. ACM Transactions on Multimedia Computing, Communications, and Applications. 2025;21(9):1-19. doi:10.1145/3748654

BibTeX
@article{Liu2025,
  author = {Liu, Junle and Zhang, Yun and Guo, Zixi and Huang, Xiaoxia and Jiang, Gangyi},
  title = {Multiscale Feature Importance-Based Bit Allocation for End-to-End Feature Coding for Machines},
  journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
  year = {2025},
  volume = {21},
  number = {9},
  pages = {1--19},
  doi = {10.1145/3748654}
}
Kostenlos starten →