EUVIMEDEUVIMED entdecken
Crossref

Dual-Depth Unified Joint Optimization: Adaptive Curvature-Based Compression

Yunsong Li, Xin Zhang, Weiying Xie, Xiaoyu Chen, Daixun Li, Hangyu Ye, Leyuan Fang

IEEE Transactions on Circuits and Systems for Video Technology · 2025-11 · 35 (11) · 10959-10972

DOI: 10.1109/tcsvt.2025.3579007 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2025-11. Verfasst von Yunsong Li und 6 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 72 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Model compression methods such as pruning and quantization have been proposed to facilitate the deployment of convolutional neural networks (CNNs) on resource-constrained devices. Existing methods aim to combine the two for simultaneous improvement in compression ratio and runtime efficiency. However, most of the joint methods adopt linear tandem structures. Due to the lack of a unified framework, different optimization directions result in suboptimal solutions, especially when the compression ratio is extremely high. In this paper, we propose a novel adaptive curvature-based compression (ACC) method, which achieves a dual-depth unified joint optimization of pruning and quantization. In the first depth, we unify the pruning and quantization criteria using mean curvature, which leverages the discrete nature of image data and the continuum theory of differential geometry. In the second depth, we replace the traditional training process in the joint pruning-quantization method with curvature-aware knowledge distillation (CKD), unifying the two-stage approach into a simple but powerful parallel step. Our method is effective and interpretable by utilizing inherent properties to promote the understanding of information distribution and the importance of feature maps. Extensive experiments on multiple advanced benchmarks and diverse downstream task datasets have validated the superiority and generalizability of our ACC. Notably, we can achieve a 1.05% Top-1 accuracy improvement over the baseline under an extreme compression ratio of $454.55\times $ , outperforming existing state-of-the-art (SOTA) methods.

Förderung

  • National Natural Science Foundation of China
  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Li, Y., Zhang, X., Xie, W., Chen, X., Li, D., Ye, H., & Fang, L. (2025). Dual-Depth Unified Joint Optimization: Adaptive Curvature-Based Compression. IEEE Transactions on Circuits and Systems for Video Technology, 35(11), 10959-10972. https://doi.org/10.1109/tcsvt.2025.3579007

Vancouver

Li Y, Zhang X, Xie W, Chen X, Li D, Ye H, et al. Dual-Depth Unified Joint Optimization: Adaptive Curvature-Based Compression. IEEE Transactions on Circuits and Systems for Video Technology. 2025;35(11):10959-10972. doi:10.1109/tcsvt.2025.3579007

BibTeX
@article{Li2025,
  author = {Li, Yunsong and Zhang, Xin and Xie, Weiying and Chen, Xiaoyu and Li, Daixun and Ye, Hangyu and Fang, Leyuan},
  title = {Dual-Depth Unified Joint Optimization: Adaptive Curvature-Based Compression},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2025},
  volume = {35},
  number = {11},
  pages = {10959--10972},
  doi = {10.1109/tcsvt.2025.3579007}
}
Kostenlos starten →