# Deep Residual Compensation Convolutional Network without Backpropagation

arXiv: https://arxiv.org/abs/2301.11663 · HTML: https://mlsanity.com/paper/2301.11663/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 23 references that are in the map.
- First posted on arXiv 27 Jan 2023.

## Builds on (most cited first, 11 of 11)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Network In Network](https://mlsanity.com/paper/1312.4400/) (2013)
- [Maxout Networks](https://mlsanity.com/paper/1302.4389/) (2013)
- [The History Began from AlexNet: A Comprehensive Survey on Deep Learning Approaches](https://mlsanity.com/paper/1803.01164/) (2018)
- [PCANet: A Simple Deep Learning Baseline for Image Classification?](https://mlsanity.com/paper/1404.3606/) (2014)
- [Stochastic Pooling for Regularization of Deep Convolutional Neural Networks](https://mlsanity.com/paper/1301.3557/) (2013)
- [Convolutional Xformers for Vision](https://mlsanity.com/paper/2201.10271/) (2022)
- [DCTNet : A Simple Learning-free Approach for Face Recognition](https://mlsanity.com/paper/1507.02049/) (2015)
- [PCANet-II: When PCANet Meets the Second Order Pooling](https://mlsanity.com/paper/1710.00166/) (2017)

## Abstract (arXiv)

PCANet and its variants provided good accuracy results for classification tasks. However, despite the importance of network depth in achieving good classification accuracy, these networks were trained with a maximum of nine layers. In this paper, we introduce a residual compensation convolutional network, which is the first PCANet-like network trained with hundreds of layers while improving classification accuracy. The design of the proposed network consists of several convolutional layers, each followed by post-processing steps and a classifier. To correct the classification errors and significantly increase the network's depth, we train each layer with new labels derived from the residual information of all its preceding layers. This learning mechanism is accomplished by traversing the network's layers in a single forward pass without backpropagation or gradient computations. Our experiments on four distinct classification benchmarks (MNIST, CIFAR-10, CIFAR-100, and TinyImageNet) show that our deep network outperforms all existing PCANet-like networks and is competitive with several traditional gradient-based models.