# Group Ensemble: Learning an Ensemble of ConvNets in a single ConvNet

arXiv: https://arxiv.org/abs/2007.00649 · HTML: https://mlsanity.com/paper/2007.00649/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jul 2020.

## Built on by (most cited first, 8 of 8)

- [Packed-Ensembles for Efficient Uncertainty Estimation](https://mlsanity.com/paper/2210.09184/) (2022)
- [Decentralized Low-Latency Collaborative Inference via Ensembles on the Edge](https://mlsanity.com/paper/2206.03165/) (2022)
- [Easy Ensemble: Simple Deep Ensemble Learning for Sensor-Based Human Activity Recognition](https://mlsanity.com/paper/2203.04153/) (2022)
- [Network Fission Ensembles for Low-Cost Self-Ensembles](https://mlsanity.com/paper/2408.02301/) (2024)
- [Low-Cost Self-Ensembles Based on Multi-Branch Transformation and Grouped Convolution](https://mlsanity.com/paper/2408.02307/) (2024)
- [Noisy Deep Ensemble: Accelerating Deep Ensemble Learning via Noise Injection](https://mlsanity.com/paper/2504.05677/) (2025)
- [OxEnsemble: Fair Ensembles for Low-Data Classification](https://mlsanity.com/paper/2512.09665/) (2025)
- [Multi-Narrow Transformation as a Single-Model Ensemble: Boundary Conditions, Mechanisms, and Failure Modes](https://mlsanity.com/paper/2605.11530/) (2026)

## Abstract (arXiv)

Ensemble learning is a general technique to improve accuracy in machine learning. However, the heavy computation of a ConvNets ensemble limits its usage in deep learning. In this paper, we present Group Ensemble Network (GENet), an architecture incorporating an ensemble of ConvNets in a single ConvNet. Through a shared-base and multi-head structure, GENet is divided into several groups to make explicit ensemble learning possible in a single ConvNet. Owing to group convolution and the shared-base, GENet can fully leverage the advantage of explicit ensemble learning while retaining the same computation as a single ConvNet. Additionally, we present Group Averaging, Group Wagging and Group Boosting as three different strategies to aggregate these ensemble members. Finally, GENet outperforms larger single networks, standard ensembles of smaller networks, and other recent state-of-the-art methods on CIFAR and ImageNet. Specifically, group ensemble reduces the top-1 error by 1.83% for ResNeXt-50 on ImageNet. We also demonstrate its effectiveness on action recognition and object detection tasks.