Journal Article

DZNE-2026-01049

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Adaptive Aggregation of Monte Carlo Augmented Decomposed Filters for Efficient Group-Equivariant Convolutional Neural Network.

Zhao, W. ; Wichtmann, B. D.DZNE* ; Albert, S. ; Schmitt, A.Extern* ; Zollner, F. G. ; Hesser, J. W.

2026

This record in other databases:    

Please use a persistent id in citations: doi:10.1109/TPAMI.2026.3672711

Abstract: Group-equivariant convolutional neural networks (G-CNN) heavily rely on parameter sharing to increase CNN's data efficiency and performance. However, the parameter-sharing strategy greatly increases the computational burden for each added parameter, which hampers its application to deep neural network models. In this paper, we address these problems by proposing a non-parameter-sharing approach for group equivariant neural networks. The proposed methods adaptively aggregate a diverse range of filters by a weighted sum of stochastically augmented decomposed filters. We give theoretical proof about how the group equivariance can be achieved by our methods. Our method applies to both continuous and discrete groups, where the augmentation is implemented using Monte Carlo sampling and bootstrap resampling, respectively. Our methods also serve as an efficient extension of standard CNN. The experiments show that our method outperforms parameter-sharing group equivariant networks and enhances the performance of standard CNNs in image classification and denoising tasks, by using suitable filter bases to build efficient lightweight networks.

Note: Missing Journal: IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE Trans. Pattern Anal. Mach. Intell.) = 2160-92921939-3539 (import from CrossRef, PubMed, , Journals: pub.dzne.de)

---

Contributing Institute(s):

1. Clinical Neuroimaging (AG Radbruch)

Research Program(s):

1. 353 - Clinical and Health Care Research (POF4-353) (POF4-353)

---