# Reducing Domain Gap by Reducing Style Bias

arXiv: https://arxiv.org/abs/1910.11645 · HTML: https://mlsanity.com/paper/1910.11645/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Oct 2019.

## Built on by (most cited first, 30 of 35)

- [SWAD: Domain Generalization by Seeking Flat Minima](https://mlsanity.com/paper/2102.08604/) (2021)
- [SelfReg: Self-supervised Contrastive Regularization for Domain Generalization](https://mlsanity.com/paper/2104.09841/) (2021)
- [Causality Inspired Representation Learning for Domain Generalization](https://mlsanity.com/paper/2203.14237/) (2022)
- [Model-Based Domain Generalization](https://mlsanity.com/paper/2102.11436/) (2021)
- [OoD-Bench: Quantifying and Understanding Two Dimensions of Out-of-Distribution Generalization](https://mlsanity.com/paper/2106.03721/) (2021)
- [Test-time Batch Statistics Calibration for Covariate Shift](https://mlsanity.com/paper/2110.04065/) (2021)
- [Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-of-Experts](https://mlsanity.com/paper/2210.03885/) (2022)
- [Quantifying and Improving Transferability in Domain Generalization](https://mlsanity.com/paper/2106.03632/) (2021)
- [Does enhanced shape bias improve neural network robustness to common corruptions?](https://mlsanity.com/paper/2104.09789/) (2021)
- [WEDGE: Web-Image Assisted Domain Generalization for Semantic Segmentation](https://mlsanity.com/paper/2109.14196/) (2021)
- [Adapting to Distribution Shift by Visual Domain Prompt Generation](https://mlsanity.com/paper/2405.02797/) (2024)
- [The Two Dimensions of Worst-case Training and the Integrated Effect for Out-of-domain Generalization](https://mlsanity.com/paper/2204.04384/) (2022)
- [Learning Representations that Support Robust Transfer of Predictors](https://mlsanity.com/paper/2110.09940/) (2021)
- [Improving Out-of-Distribution Generalization by Adversarial Training with Structured Priors](https://mlsanity.com/paper/2210.06807/) (2022)
- [FisherTune: Fisher-Guided Robust Tuning of Vision Foundation Models for Domain Generalized Segmentation](https://mlsanity.com/paper/2503.17940/) (2025)
- [Towards Data-Free Domain Generalization](https://mlsanity.com/paper/2110.04545/) (2021)
- [Seeking Consistent Flat Minima for Better Domain Generalization via Refining Loss Landscapes](https://mlsanity.com/paper/2412.13573/) (2024)
- [Adaptive Domain Generalization via Online Disagreement Minimization](https://mlsanity.com/paper/2208.01996/) (2022)
- [SFP: Spurious Feature-targeted Pruning for Out-of-Distribution Generalization](https://mlsanity.com/paper/2305.11615/) (2023)
- [HCVP: Leveraging Hierarchical Contrastive Visual Prompt for Domain Generalization](https://mlsanity.com/paper/2401.09716/) (2024)
- [Encouraging Intra-Class Diversity Through a Reverse Contrastive Loss for Better Single-Source Domain Generalization](https://mlsanity.com/paper/2106.07916/) (2021)
- [Regularization Penalty Optimization for Addressing Data Quality Variance in OoD Algorithms](https://mlsanity.com/paper/2206.05749/) (2022)
- [Improving Generalization with Domain Convex Game](https://mlsanity.com/paper/2303.13297/) (2023)
- [A Causal Framework to Unify Common Domain Generalization Approaches](https://mlsanity.com/paper/2307.06825/) (2023)
- [Explainability-aided Domain Generalization for Image Classification](https://mlsanity.com/paper/2104.01742/) (2021)
- [Discovery of New Multi-Level Features for Domain Generalization via Knowledge Corruption](https://mlsanity.com/paper/2109.04320/) (2021)
- [Bag of Tricks for Domain Adaptive Multi-Object Tracking](https://mlsanity.com/paper/2205.15609/) (2022)
- [Domain Generalization via Selective Consistency Regularization for Time Series Classification](https://mlsanity.com/paper/2206.07876/) (2022)
- [MSSIDD: A Benchmark for Multi-Sensor Denoising](https://mlsanity.com/paper/2411.11562/) (2024)
- [Automated Domain Discovery from Multiple Sources to Improve Zero-Shot Generalization](https://mlsanity.com/paper/2112.09802/) (2021)

## Abstract (arXiv)

Convolutional Neural Networks (CNNs) often fail to maintain their performance when they confront new test domains, which is known as the problem of domain shift. Recent studies suggest that one of the main causes of this problem is CNNs' strong inductive bias towards image styles (i.e. textures) which are sensitive to domain changes, rather than contents (i.e. shapes). Inspired by this, we propose to reduce the intrinsic style bias of CNNs to close the gap between domains. Our Style-Agnostic Networks (SagNets) disentangle style encodings from class categories to prevent style biased predictions and focus more on the contents. Extensive experiments show that our method effectively reduces the style bias and makes the model more robust under domain shift. It achieves remarkable performance improvements in a wide range of cross-domain tasks including domain generalization, unsupervised domain adaptation, and semi-supervised domain adaptation on multiple datasets.