# Domain Generalization using Ensemble Learning

arXiv: https://arxiv.org/abs/2103.10257 · HTML: https://mlsanity.com/paper/2103.10257/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 38 references that are in the map.
- First posted on arXiv 18 Mar 2021.

## Builds on (most cited first, 6 of 6)

- [Understanding deep learning requires rethinking generalization](https://mlsanity.com/paper/1611.03530/) (2016)
- [Best sources forward: domain generalization through source-specific nets](https://mlsanity.com/paper/1806.05810/) (2018)
- [Anomaly Detection based on Zero-Shot Outlier Synthesis and Hierarchical Feature Distillation](https://mlsanity.com/paper/2010.05119/) (2020)
- [Multi-label Class-imbalanced Action Recognition in Hockey Videos via 3D Convolutional Neural Networks](https://mlsanity.com/paper/1709.01421/) (2017)
- [Application of Low-resource Machine Translation Techniques to Russian-Tatar Language Pair](https://mlsanity.com/paper/1910.00368/) (2019)
- [SART - Similarity, Analogies, and Relatedness for Tatar Language: New Benchmark Datasets for Word Embeddings Evaluation](https://mlsanity.com/paper/1904.00365/) (2019)

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

- [Diverse Weight Averaging for Out-of-Distribution Generalization](https://mlsanity.com/paper/2205.09739/) (2022)
- [Test-Time Adaptation via Self-Training with Nearest Neighbor Information](https://mlsanity.com/paper/2207.10792/) (2022)
- [QT-DoG: Quantization-aware Training for Domain Generalization](https://mlsanity.com/paper/2410.06020/) (2024)
- [MEPG: A Minimalist Ensemble Policy Gradient Framework for Deep Reinforcement Learning](https://mlsanity.com/paper/2109.10552/) (2021)

## Abstract (arXiv)

Domain generalization is a sub-field of transfer learning that aims at bridging the gap between two different domains in the absence of any knowledge about the target domain. Our approach tackles the problem of a model's weak generalization when it is trained on a single source domain. From this perspective, we build an ensemble model on top of base deep learning models trained on a single source to enhance the generalization of their collective prediction. The results achieved thus far have demonstrated promising improvements of the ensemble over any of its base learners.