# Ensemble learning in CNN augmented with fully connected subnetworks

arXiv: https://arxiv.org/abs/2003.08562 · HTML: https://mlsanity.com/paper/2003.08562/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Mar 2020.

## Built on by (most cited first, 9 of 9)

- [XnODR and XnIDR: Two Accurate and Fast Fully Connected Layers For Convolutional Neural Networks](https://mlsanity.com/paper/2111.10854/) (2021)
- [Laplace-HDC: Understanding the geometry of binary hyperdimensional computing](https://mlsanity.com/paper/2404.10759/) (2024)
- [Automated Semiconductor Defect Inspection in Scanning Electron Microscope Images: a Systematic Review](https://mlsanity.com/paper/2308.08376/) (2023)
- [Accelerating Machine Learning via the Weber-Fechner Law](https://mlsanity.com/paper/2204.11834/) (2022)
- [LR-Net: A Block-based Convolutional Neural Network for Low-Resolution Image Classification](https://mlsanity.com/paper/2207.09531/) (2022)
- [CoV-TI-Net: Transferred Initialization with Modified End Layer for COVID-19 Diagnosis](https://mlsanity.com/paper/2209.09556/) (2022)
- [Classification of Non-native Handwritten Characters Using Convolutional Neural Network](https://mlsanity.com/paper/2406.04511/) (2024)
- [ConstellationNet: Reinventing Spatial Clustering through GNNs](https://mlsanity.com/paper/2503.07643/) (2025)
- [Single-Qudit Quantum Neural Networks for Multiclass Classification](https://mlsanity.com/paper/2503.09269/) (2025)

## Abstract (arXiv)

Convolutional Neural Networks (CNNs) have shown remarkable performance in general object recognition tasks. In this paper, we propose a new model called EnsNet which is composed of one base CNN and multiple Fully Connected SubNetworks (FCSNs). In this model, the set of feature-maps generated by the last convolutional layer in the base CNN is divided along channels into disjoint subsets, and these subsets are assigned to the FCSNs. Each of the FCSNs is trained independent of others so that it can predict the class label from the subset of the feature-maps assigned to it. The output of the overall model is determined by majority vote of the base CNN and the FCSNs. Experimental results using the MNIST, Fashion-MNIST and CIFAR-10 datasets show that the proposed approach further improves the performance of CNNs. In particular, an EnsNet achieves a state-of-the-art error rate of 0.16% on MNIST.