A Frame-Theoretic Approach to Robust Filter Pruning in Convolutional Neural Networks
IEEE Signal Processing Letters · 2026 · 33 · 1991-1995
DOI: 10.1109/lsp.2026.3691024 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Signal Processing Letters, 2026. Verfasst von Pradyumna Pradhan und 2 weiteren Autor:innen. Die Arbeit nennt 42 Literaturangaben. Gefördert von: Science and Engineering Research Board, Govt. of India, NBHM, Govt. of India.
Abstract (Originalsprache)
Filter pruning method is an effective approach to eliminate redundant filters in convolutional neural networks. Most of the existing techniques rely on threshold parameters for filter selection and employ multi-shot pruning, resulting in increased computational overhead. In addition, many methods primarily optimize test accuracy while overlooking robustness to noise, which is critical in practical and safety-critical applications. Since Incoherent Unit Norm Tight Frames (IUNTFs) are inherently robust to noise, we propose a filter pruning technique that removes redundant filters such that the retained set approximates an IUNTF structure. This structure enhances noise robustness and promotes the extraction of diverse and complementary features. Unlike conventional approaches, the proposed framework requires no threshold tuning and adopts a one-shot pruning strategy. Experimental results on the CIFAR-10 dataset using VGG-16, ResNet-56, and GoogLeNet demonstrate that the proposed method achieves robustness under noise and improved accuracy compared to existing approaches while pruning 85.12%, 57%, and 59% of the parameters and 69.66%, 57%, and 58% of the FLOPs, respectively.
Förderung
- Science and Engineering Research Board
- Govt. of India
- NBHM, Govt. of India
Zitieren
APA
Pradhan, P., Sasmal, P., & Randhi, R. (2026). A Frame-Theoretic Approach to Robust Filter Pruning in Convolutional Neural Networks. IEEE Signal Processing Letters, 33, 1991-1995. https://doi.org/10.1109/lsp.2026.3691024
Vancouver
Pradhan P, Sasmal P, Randhi R. A Frame-Theoretic Approach to Robust Filter Pruning in Convolutional Neural Networks. IEEE Signal Processing Letters. 2026;33:1991-1995. doi:10.1109/lsp.2026.3691024
BibTeX
@article{Pradhan2026,
author = {Pradhan, Pradyumna and Sasmal, Pradip and Randhi, Ramunaidu},
title = {A Frame-Theoretic Approach to Robust Filter Pruning in Convolutional Neural Networks},
journal = {IEEE Signal Processing Letters},
year = {2026},
volume = {33},
pages = {1991--1995},
doi = {10.1109/lsp.2026.3691024}
}
EUVIMED