# CoShNet: A Hybrid Complex Valued Neural Network using Shearlets

arXiv: https://arxiv.org/abs/2208.06882 · HTML: https://mlsanity.com/paper/2208.06882/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 53 references that are in the map.
- First posted on arXiv 14 Aug 2022.

## Builds on (most cited first, 20 of 20)

- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)](https://mlsanity.com/paper/1511.07289/) (2015)
- [Opening the Black Box of Deep Neural Networks via Information](https://mlsanity.com/paper/1703.00810/) (2017)
- [ResNet strikes back: An improved training procedure in timm](https://mlsanity.com/paper/2110.00476/) (2021)
- [How to Escape Saddle Points Efficiently](https://mlsanity.com/paper/1703.00887/) (2017)
- [Tensorizing Neural Networks](https://mlsanity.com/paper/1509.06569/) (2015)
- [Deep Complex Networks](https://mlsanity.com/paper/1705.09792/) (2017)
- [Torch.manual_seed(3407) is all you need: On the influence of random seeds in deep learning architectures for computer vision](https://mlsanity.com/paper/2109.08203/) (2021)
- [Deep Roto-Translation Scattering for Object Classification](https://mlsanity.com/paper/1412.8659/) (2014)
- [Gradient Descent Converges to Minimizers](https://mlsanity.com/paper/1602.04915/) (2016)
- [DCFNet: Deep Neural Network with Decomposed Convolutional Filters](https://mlsanity.com/paper/1802.04145/) (2018)
- [Complex-Valued vs. Real-Valued Neural Networks for Classification Perspectives: An Example on Non-Circular Data](https://mlsanity.com/paper/2009.08340/) (2020)
- [Evaluation of Complex-Valued Neural Networks on Real-Valued Classification Tasks](https://mlsanity.com/paper/1811.12351/) (2018)
- [Deep Convolutional Neural Networks Based on Semi-Discrete Frames](https://mlsanity.com/paper/1504.05487/) (2015)
- [Edge, Ridge, and Blob Detection with Symmetric Molecules](https://mlsanity.com/paper/1901.09723/) (2019)
- [Shearlets as Feature Extractor for Semantic Edge Detection: The Model-Based and Data-Driven Realm](https://mlsanity.com/paper/1911.12159/) (2019)
- [Learning Multi-Layer Transform Models](https://mlsanity.com/paper/1810.08323/) (2018)
- [ChaRRNets: Channel Robust Representation Networks for RF Fingerprinting](https://mlsanity.com/paper/2105.03568/) (2021)

## Built on by (most cited first, 1 of 1)

- [Impact of PolSAR pre-processing and balancing methods on complex-valued neural networks segmentation tasks](https://mlsanity.com/paper/2210.17419/) (2022)

## Abstract (arXiv)

In a hybrid neural network, the expensive convolutional layers are replaced by a non-trainable fixed transform with a great reduction in parameters. In previous works, good results were obtained by replacing the convolutions with wavelets. However, wavelet based hybrid network inherited wavelet's lack of vanishing moments along curves and its axis-bias. We propose to use Shearlets with its robust support for important image features like edges, ridges and blobs. The resulting network is called Complex Shearlets Network (CoShNet). It was tested on Fashion-MNIST against ResNet-50 and Resnet-18, obtaining 92.2% versus 90.7% and 91.8% respectively. The proposed network has 49.9k parameters versus ResNet-18 with 11.18m and use 52 times fewer FLOPs. Finally, we trained in under 20 epochs versus 200 epochs required by ResNet and do not need any hyperparameter tuning nor regularization. Code: https://github.com/Ujjawal-K-Panchal/coshnet