Convolutional Neural Networks Do Work with Pre-Defined Filters
Not on the map. Why?
Abstract (arXiv)
We present a novel class of Convolutional Neural Networks called Pre-defined Filter Convolutional Neural Networks (PFCNNs), where all nxn convolution kernels with n>1 are pre-defined and constant during training. It involves a special form of depthwise convolution operation called a Pre-defined Filter Module (PFM). In the channel-wise convolution part, the 1xnxn kernels are drawn from a fixed pool of only a few (16) different pre-defined kernels. In the 1x1 convolution part linear combinations of the pre-defined filter outputs are learned. Despite this harsh restriction, complex and discriminative features are learned. These findings provide a novel perspective on the way how information is processed within deep CNNs. We discuss various properties of PFCNNs and prove their effectiveness using the popular datasets Caltech101, CIFAR10, CUB-200-2011, FGVC-Aircraft, Flowers102, and Stanford Cars. Our implementation of PFCNNs is provided on Github https://github.com/Criscraft/PredefinedFilterNetworks
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 12 of its 26 references that are in the map. First posted on arXiv 27 Nov 2024.
Builds on
12 of 26 references.
References · 12
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
- 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
- 2013Fine-Grained Visual Classification of Aircraftcited by 1,701
- 2018Reconciling modern machine learning practice and the bias-variance trade-offcited by 919
- 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
- 2019Large Batch Optimization for Deep Learning: Training BERT in 76 minutescited by 671
- 2014Understanding Deep Image Representations by Inverting Themcited by 399
- 2015Understanding Neural Networks Through Deep Visualizationcited by 332
- 2022CNN Filter DB: An Empirical Investigation of Trained Convolutional Filterscited by 20
- 2017Deep Convolutional Neural Networks as Generic Feature Extractorscited by 10
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.