Adaptive aggregation of Monte Carlo augmented decomposed filters for efficient group-equivariant convolutional neural network
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 netwo...
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Article (Journal) |
| Lingua: | inglese |
| Pubblicazione: |
AUGUST 2026
|
| In: |
IEEE transactions on pattern analysis and machine intelligence
Year: 2026, Volume: 48, Fascicolo: 8, Pages: 8781-8797 |
| ISSN: | 1939-3539 |
| DOI: | 10.1109/TPAMI.2026.3672711 |
| Accesso online: | Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1109/TPAMI.2026.3672711 Verlag, lizenzpflichtig, Volltext: https://ieeexplore.ieee.org/document/11429096 
|
| Note sull'autore: | Wenzhao Zhao, Member, IEEE, Barbara D. Wichtmann, Steffen Albert, Angelika Maurer, Frank G. Zöllner, Senior Member, IEEE, and Jürgen W. Hesser |
| Riassunto: | 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. |
|---|---|
| Descrizione del documento: | Online veröffentlicht: 10. März 2026 Gesehen am 04.08.2026 |
| Descrizione fisica: | Online Resource |
| ISSN: | 1939-3539 |
| DOI: | 10.1109/TPAMI.2026.3672711 |