# Gabor filter incorporated CNN for compression

arXiv: https://arxiv.org/abs/2110.15644 · HTML: https://mlsanity.com/paper/2110.15644/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 44 references that are in the map.
- First posted on arXiv 29 Oct 2021.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [Deep Networks with Stochastic Depth](https://mlsanity.com/paper/1603.09382/) (2016)
- [Channel Pruning for Accelerating Very Deep Neural Networks](https://mlsanity.com/paper/1707.06168/) (2017)
- [Learning Efficient Convolutional Networks through Network Slimming](https://mlsanity.com/paper/1708.06519/) (2017)
- [Cyclical Learning Rates for Training Neural Networks](https://mlsanity.com/paper/1506.01186/) (2015)
- [Stand-Alone Self-Attention in Vision Models](https://mlsanity.com/paper/1906.05909/) (2019)
- [Learning Structured Sparsity in Deep Neural Networks](https://mlsanity.com/paper/1608.03665/) (2016)
- [ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases](https://mlsanity.com/paper/2103.10697/) (2021)
- [ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression](https://mlsanity.com/paper/1707.06342/) (2017)
- [Bottleneck Transformers for Visual Recognition](https://mlsanity.com/paper/2101.11605/) (2021)
- [A Survey of Model Compression and Acceleration for Deep Neural Networks](https://mlsanity.com/paper/1710.09282/) (2017)
- [Dynamic Network Surgery for Efficient DNNs](https://mlsanity.com/paper/1608.04493/) (2016)
- [Predicting Parameters in Deep Learning](https://mlsanity.com/paper/1306.0543/) (2013)
- [Structured Pruning of Deep Convolutional Neural Networks](https://mlsanity.com/paper/1512.08571/) (2015)
- [Accelerating Very Deep Convolutional Networks for Classification and Detection](https://mlsanity.com/paper/1505.06798/) (2015)
- [Gabor Convolutional Networks](https://mlsanity.com/paper/1705.01450/) (2017)
- [Data-dependent Initializations of Convolutional Neural Networks](https://mlsanity.com/paper/1511.06856/) (2015)
- [Gabor Filter Assisted Energy Efficient Fast Learning Convolutional Neural Networks](https://mlsanity.com/paper/1705.04748/) (2017)

## Abstract (arXiv)

Convolutional neural networks (CNNs) are remarkably successful in many computer vision tasks. However, the high cost of inference is problematic for embedded and real-time systems, so there are many studies on compressing the networks. On the other hand, recent advances in self-attention models showed that convolution filters are preferable to self-attention in the earlier layers, which indicates that stronger inductive biases are better in the earlier layers. As shown in convolutional filters, strong biases can train specific filters and construct unnecessarily filters to zero. This is analogous to classical image processing tasks, where choosing the suitable filters makes a compact dictionary to represent features. We follow this idea and incorporate Gabor filters in the earlier layers of CNNs for compression. The parameters of Gabor filters are learned through backpropagation, so the features are restricted to Gabor filters. We show that the first layer of VGG-16 for CIFAR-10 has 192 kernels/features, but learning Gabor filters requires an average of 29.4 kernels. Also, using Gabor filters, an average of 83% and 94% of kernels in the first and the second layer, respectively, can be removed on the altered ResNet-20, where the first five layers are exchanged with two layers of larger kernels for CIFAR-10.