# Multichannel Orthogonal Transform-Based Perceptron Layers for Efficient ResNets

arXiv: https://arxiv.org/abs/2303.06797 · HTML: https://mlsanity.com/paper/2303.06797/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 55 references that are in the map.
- First posted on arXiv 13 Mar 2023.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [CCNet: Criss-Cross Attention for Semantic Segmentation](https://mlsanity.com/paper/1811.11721/) (2018)
- [BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation](https://mlsanity.com/paper/1808.00897/) (2018)
- [Importance Estimation for Neural Network Pruning](https://mlsanity.com/paper/1906.10771/) (2019)
- [Fast-SCNN: Fast Semantic Segmentation Network](https://mlsanity.com/paper/1902.04502/) (2019)
- [Multi-level Wavelet Convolutional Neural Networks](https://mlsanity.com/paper/1907.03128/) (2019)
- [Learning Compressed Transforms with Low Displacement Rank](https://mlsanity.com/paper/1810.02309/) (2018)
- [Harmonic Convolutional Networks based on Discrete Cosine Transform](https://mlsanity.com/paper/2001.06570/) (2020)
- [Fast Walsh-Hadamard Transform and Smooth-Thresholding Based Binary Layers in Deep Neural Networks](https://mlsanity.com/paper/2104.07085/) (2021)
- [Block Walsh-Hadamard Transform Based Binary Layers in Deep Neural Networks](https://mlsanity.com/paper/2201.02711/) (2022)
- [Energy Efficient Hadamard Neural Networks](https://mlsanity.com/paper/1805.05421/) (2018)
- [Compressing the Input for CNNs with the First-Order Scattering Transform](https://mlsanity.com/paper/1809.10200/) (2018)
- [Less is More: Accelerating Faster Neural Networks Straight from JPEG](https://mlsanity.com/paper/2104.00185/) (2021)
- [Federated Momentum Contrastive Clustering](https://mlsanity.com/paper/2206.05093/) (2022)
- [Discrete Cosine Transform Based Causal Convolutional Neural Network for Drift Compensation in Chemical Sensors](https://mlsanity.com/paper/2011.06681/) (2020)
- [A Simulation Study to Evaluate the Performance of the Cauchy Proximal Operator in Despeckling SAR Images of the Sea Surface](https://mlsanity.com/paper/2012.06657/) (2020)

## Built on by (most cited first, 2 of 2)

- [Spectral Compression Transformer with Line Pose Graph for Monocular 3D Human Pose Estimation](https://mlsanity.com/paper/2505.21309/) (2025)
- [ShearFuse-UNet: Hadamard, DCT, and Shearlet Transform Fusion for Next-Day Wildfire Spread Prediction](https://mlsanity.com/paper/2606.14071/) (2026)

## Abstract (arXiv)

In this paper, we propose a set of transform-based neural network layers as an alternative to the 3×3 Conv2D layers in Convolutional Neural Networks (CNNs). The proposed layers can be implemented based on orthogonal transforms such as the Discrete Cosine Transform (DCT), Hadamard transform (HT), and biorthogonal Block Wavelet Transform (BWT). Furthermore, by taking advantage of the convolution theorems, convolutional filtering operations are performed in the transform domain using element-wise multiplications. Trainable soft-thresholding layers, that remove noise in the transform domain, bring nonlinearity to the transform domain layers. Compared to the Conv2D layer, which is spatial-agnostic and channel-specific, the proposed layers are location-specific and channel-specific. Moreover, these proposed layers reduce the number of parameters and multiplications significantly while improving the accuracy results of regular ResNets on the ImageNet-1K classification task. Furthermore, they can be inserted with a batch normalization layer before the global average pooling layer in the conventional ResNets as an additional layer to improve classification accuracy.