# Robust and Generalizable Visual Representation Learning via Random Convolutions

arXiv: https://arxiv.org/abs/2007.13003 · HTML: https://mlsanity.com/paper/2007.13003/

## Key facts

- Cited by 142 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jul 2020.

## Built on by (most cited first, 30 of 142)

- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Robust Test-Time Adaptation in Dynamic Scenarios](https://mlsanity.com/paper/2303.13899/) (2023)
- [Fake it till you make it: Learning transferable representations from synthetic ImageNet clones](https://mlsanity.com/paper/2212.08420/) (2022)
- [Learning to Diversify for Single Domain Generalization](https://mlsanity.com/paper/2108.11726/) (2021)
- [Uncertainty Modeling for Out-of-Distribution Generalization](https://mlsanity.com/paper/2202.03958/) (2022)
- [Causality-inspired Single-source Domain Generalization for Medical Image Segmentation](https://mlsanity.com/paper/2111.12525/) (2021)
- [Diffusion Models for Image Restoration and Enhancement: A Comprehensive Survey](https://mlsanity.com/paper/2308.09388/) (2023)
- [Broaden Your Views for Self-Supervised Video Learning](https://mlsanity.com/paper/2103.16559/) (2021)
- [Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation](https://mlsanity.com/paper/2107.00644/) (2021)
- [Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorization](https://mlsanity.com/paper/2106.06916/) (2021)
- [Improved Test-Time Adaptation for Domain Generalization](https://mlsanity.com/paper/2304.04494/) (2023)
- [Rethinking Data Augmentation for Single-source Domain Generalization in Medical Image Segmentation](https://mlsanity.com/paper/2211.14805/) (2022)
- [Semi-Supervised Domain Generalization with Stochastic StyleMatch](https://mlsanity.com/paper/2106.00592/) (2021)
- [BayeSeg: Bayesian Modeling for Medical Image Segmentation with Interpretable Generalizability](https://mlsanity.com/paper/2303.01710/) (2023)
- [Feature Stylization and Domain-aware Contrastive Learning for Domain Generalization](https://mlsanity.com/paper/2108.08596/) (2021)
- [Compound Domain Generalization via Meta-Knowledge Encoding](https://mlsanity.com/paper/2203.13006/) (2022)
- [Multiple-environment Self-adaptive Network for Aerial-view Geo-localization](https://mlsanity.com/paper/2204.08381/) (2022)
- [Discrete Representations Strengthen Vision Transformer Robustness](https://mlsanity.com/paper/2111.10493/) (2021)
- [Progressive Random Convolutions for Single Domain Generalization](https://mlsanity.com/paper/2304.00424/) (2023)
- [HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentation](https://mlsanity.com/paper/2305.13031/) (2023)
- [Domain Generalization by Learning and Removing Domain-specific Features](https://mlsanity.com/paper/2212.07101/) (2022)
- [MaxStyle: Adversarial Style Composition for Robust Medical Image Segmentation](https://mlsanity.com/paper/2206.01737/) (2022)
- [DeSAM: Decoupled Segment Anything Model for Generalizable Medical Image Segmentation](https://mlsanity.com/paper/2306.00499/) (2023)
- [Taxonomy of Machine Learning Safety: A Survey and Primer](https://mlsanity.com/paper/2106.04823/) (2021)
- [Domain generalization of 3D semantic segmentation in autonomous driving](https://mlsanity.com/paper/2212.04245/) (2022)
- [Federated Domain Generalization: A Survey](https://mlsanity.com/paper/2306.01334/) (2023)
- [Generalized but not Robust? Comparing the Effects of Data Modification Methods on Out-of-Domain Generalization and Adversarial Robustness](https://mlsanity.com/paper/2203.07653/) (2022)
- [Boosting Robustness of Image Matting with Context Assembling and Strong Data Augmentation](https://mlsanity.com/paper/2201.06889/) (2022)
- [Adversarial Consistency for Single Domain Generalization in Medical Image Segmentation](https://mlsanity.com/paper/2206.13737/) (2022)
- [Adversarial Bayesian Augmentation for Single-Source Domain Generalization](https://mlsanity.com/paper/2307.09520/) (2023)

## Abstract (arXiv)

While successful for various computer vision tasks, deep neural networks have shown to be vulnerable to texture style shifts and small perturbations to which humans are robust. In this work, we show that the robustness of neural networks can be greatly improved through the use of random convolutions as data augmentation. Random convolutions are approximately shape-preserving and may distort local textures. Intuitively, randomized convolutions create an infinite number of new domains with similar global shapes but random local textures. Therefore, we explore using outputs of multi-scale random convolutions as new images or mixing them with the original images during training. When applying a network trained with our approach to unseen domains, our method consistently improves the performance on domain generalization benchmarks and is scalable to ImageNet. In particular, in the challenging scenario of generalizing to the sketch domain in PACS and to ImageNet-Sketch, our method outperforms state-of-art methods by a large margin. More interestingly, our method can benefit downstream tasks by providing a more robust pretrained visual representation.