# Multi-Residual Networks: Improving the Speed and Accuracy of Residual Networks

arXiv: https://arxiv.org/abs/1609.05672 · HTML: https://mlsanity.com/paper/1609.05672/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Sep 2016.

## Built on by (most cited first, 4 of 4)

- [Light Field Image Quality Assessment With Auxiliary Learning Based on Depthwise and Anglewise Separable Convolutions](https://mlsanity.com/paper/2412.07079/) (2024)
- [Computer Vision Methods for the Microstructural Analysis of Materials: The State-of-the-art and Future Perspectives](https://mlsanity.com/paper/2208.04149/) (2022)
- [Excavate the potential of Single-Scale Features: A Decomposition Network for Water-Related Optical Image Enhancement](https://mlsanity.com/paper/2508.04123/) (2025)
- [Image Classification via Random Dilated Convolution with Multi-Branch Feature Extraction and Context Excitation](https://mlsanity.com/paper/2604.25188/) (2026)

## Abstract (arXiv)

In this article, we take one step toward understanding the learning behavior of deep residual networks, and supporting the observation that deep residual networks behave like ensembles. We propose a new convolutional neural network architecture which builds upon the success of residual networks by explicitly exploiting the interpretation of very deep networks as an ensemble. The proposed multi-residual network increases the number of residual functions in the residual blocks. Our architecture generates models that are wider, rather than deeper, which significantly improves accuracy. We show that our model achieves an error rate of 3.73% and 19.45% on CIFAR-10 and CIFAR-100 respectively, that outperforms almost all of the existing models. We also demonstrate that our model outperforms very deep residual networks by 0.22% (top-1 error) on the full ImageNet 2012 classification dataset. Additionally, inspired by the parallel structure of multi-residual networks, a model parallelism technique has been investigated. The model parallelism method distributes the computation of residual blocks among the processors, yielding up to 15% computational complexity improvement.