# Back-to-Bones: Rediscovering the Role of Backbones in Domain Generalization

arXiv: https://arxiv.org/abs/2209.01121 · HTML: https://mlsanity.com/paper/2209.01121/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 55 of its 76 references that are in the map.
- First posted on arXiv 2 Sep 2022.

## Builds on (most cited first, 30 of 55)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [In Search of Lost Domain Generalization](https://mlsanity.com/paper/2007.01434/) (2020)
- [Deeper, Broader and Artier Domain Generalization](https://mlsanity.com/paper/1710.03077/) (2017)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Learning to Generalize: Meta-Learning for Domain Generalization](https://mlsanity.com/paper/1710.03463/) (2017)
- [Recognition in Terra Incognita](https://mlsanity.com/paper/1807.04975/) (2018)
- [Domain Generalization via Invariant Feature Representation](https://mlsanity.com/paper/1301.2115/) (2013)
- [ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases](https://mlsanity.com/paper/2103.10697/) (2021)
- [LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference](https://mlsanity.com/paper/2104.01136/) (2021)
- [Generalizing to Unseen Domains via Adversarial Data Augmentation](https://mlsanity.com/paper/1805.12018/) (2018)
- [Domain Generalization by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1903.06864/) (2019)
- [Self-Challenging Improves Cross-Domain Generalization](https://mlsanity.com/paper/2007.02454/) (2020)

## Built on by (most cited first, 12 of 12)

- [ERM++: An Improved Baseline for Domain Generalization](https://mlsanity.com/paper/2304.01973/) (2023)
- [Domain Generalization Using Large Pretrained Models with Mixture-of-Adapters](https://mlsanity.com/paper/2310.11031/) (2023)
- [Vision transformers in domain adaptation and domain generalization: a study of robustness](https://mlsanity.com/paper/2404.04452/) (2024)
- [Domain Generalization for Crop Segmentation with Standardized Ensemble Knowledge Distillation](https://mlsanity.com/paper/2304.01029/) (2023)
- [What's in a Latent? Leveraging Diffusion Latent Space for Domain Generalization](https://mlsanity.com/paper/2503.06698/) (2025)
- [Mind the Backbone: Minimizing Backbone Distortion for Robust Object Detection](https://mlsanity.com/paper/2303.14744/) (2023)
- [Synergy and Diversity in CLIP: Enhancing Performance Through Adaptive Backbone Ensembling](https://mlsanity.com/paper/2405.17139/) (2024)
- [On the Robustness of Human-Object Interaction Detection against Distribution Shift](https://mlsanity.com/paper/2506.18021/) (2025)
- [Physical Knot Classification Beyond Accuracy: A Benchmark and Diagnostic Study](https://mlsanity.com/paper/2603.23286/) (2026)
- [Evaluation of Randomization through Style Transfer for Enhanced Domain Generalization](https://mlsanity.com/paper/2604.05616/) (2026)
- [eXplaining to Learn (eX2L): Regularization Using Contrastive Visual Explanation Pairs for Distribution Shifts](https://mlsanity.com/paper/2605.06368/) (2026)
- [Beyond aggregate scores: Deployment-aware and non-compensatory benchmarking of vision-based eye-state recognition models for driver monitoring](https://mlsanity.com/paper/2606.08123/) (2026)

## Abstract (arXiv)

Domain Generalization (DG) studies the capability of a deep learning model to generalize to out-of-training distributions. In the last decade, literature has been massively filled with training methodologies that claim to obtain more abstract and robust data representations to tackle domain shifts. Recent research has provided a reproducible benchmark for DG, pointing out the effectiveness of naive empirical risk minimization (ERM) over existing algorithms. Nevertheless, researchers persist in using the same outdated feature extractors, and no attention has been given to the effects of different backbones yet. In this paper, we start back to the backbones proposing a comprehensive analysis of their intrinsic generalization capabilities, which so far have been ignored by the research community. We evaluate a wide variety of feature extractors, from standard residual solutions to transformer-based architectures, finding an evident linear correlation between large-scale single-domain classification accuracy and DG capability. Our extensive experimentation shows that by adopting competitive backbones in conjunction with effective data augmentation, plain ERM outperforms recent DG solutions and achieves state-of-the-art accuracy. Moreover, our additional qualitative studies reveal that novel backbones give more similar representations to same-class samples, separating different domains in the feature space. This boost in generalization capabilities leaves marginal room for DG algorithms. It suggests a new paradigm for investigating the problem, placing backbones in the spotlight and encouraging the development of consistent algorithms on top of them. The code is available at https://github.com/PIC4SeR/Back-to-Bones.