# Gabor Filter Assisted Energy Efficient Fast Learning Convolutional Neural Networks

arXiv: https://arxiv.org/abs/1705.04748 · HTML: https://mlsanity.com/paper/1705.04748/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 May 2017.

## Built on by (most cited first, 8 of 8)

- [Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities](https://mlsanity.com/paper/2210.06640/) (2022)
- [3D Segmentation with Fully Trainable Gabor Kernels and Pearson's Correlation Coefficient](https://mlsanity.com/paper/2201.03644/) (2022)
- [A multi-level interpretable sleep stage scoring system by infusing experts' knowledge into a deep network architecture](https://mlsanity.com/paper/2207.04585/) (2022)
- [On the Shift Invariance of Max Pooling Feature Maps in Convolutional Neural Networks](https://mlsanity.com/paper/2209.11740/) (2022)
- [Gabor is Enough: Interpretable Deep Denoising with a Gabor Synthesis Dictionary Prior](https://mlsanity.com/paper/2204.11146/) (2022)
- [What do CNNs Learn in the First Layer and Why? A Linear Systems Perspective](https://mlsanity.com/paper/2206.02454/) (2022)
- [Gabor filter incorporated CNN for compression](https://mlsanity.com/paper/2110.15644/) (2021)
- [Analytic Convolutional Layer: A Step to Analytic Neural Network](https://mlsanity.com/paper/2407.06087/) (2024)

## Abstract (arXiv)

Convolutional Neural Networks (CNN) are being increasingly used in computer vision for a wide range of classification and recognition problems. However, training these large networks demands high computational time and energy requirements; hence, their energy-efficient implementation is of great interest. In this work, we reduce the training complexity of CNNs by replacing certain weight kernels of a CNN with Gabor filters. The convolutional layers use the Gabor filters as fixed weight kernels, which extracts intrinsic features, with regular trainable weight kernels. This combination creates a balanced system that gives better training performance in terms of energy and time, compared to the standalone CNN (without any Gabor kernels), in exchange for tolerable accuracy degradation. We show that the accuracy degradation can be mitigated by partially training the Gabor kernels, for a small fraction of the total training cycles. We evaluated the proposed approach on 4 benchmark applications. Simple tasks like face detection and character recognition (MNIST and TiCH), were implemented using LeNet architecture. While a more complex task of object recognition (CIFAR10) was implemented on a state of the art deep CNN (Network in Network) architecture. The proposed approach yields 1.31-1.53x improvement in training energy in comparison to conventional CNN implementation. We also obtain improvement up to 1.4x in training time, up to 2.23x in storage requirements, and up to 2.2x in memory access energy. The accuracy degradation suffered by the approximate implementations is within 0-3% of the baseline.