mlsanityData to 7 Oct 2026

Rethinking Domain Generalization Baselines

arXiv 2101.09060 ↗First posted 22 Jan 2021cs.CV cs.LGcited by 26

Not on the map. Why?

Abstract (arXiv)

Despite being very powerful in standard learning settings, deep learning models can be extremely brittle when deployed in scenarios different from those on which they were trained. Domain generalization methods investigate this problem and data augmentation strategies have shown to be helpful tools to increase data variability, supporting model robustness across domains. In our work we focus on style transfer data augmentation and we present how it can be implemented with a simple and inexpensive strategy to improve generalization. Moreover, we analyze the behavior of current state of the art domain generalization methods when integrated with this augmentation solution: our thorough experimental evaluation shows that their original effect almost always disappears with respect to the augmented baseline. This issue open new scenarios for domain generalization research, highlighting the need of novel methods properly able to take advantage of the introduced data variability.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). Builds on 22 of its 31 references that are in the map. First posted on arXiv 22 Jan 2021.

Builds on

22 of 31 references.

References · 22

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  3. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  4. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
  5. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,181
  6. 2020In Search of Lost Domain Generalizationcited by 1,042
  7. 2019Learning Robust Global Representations by Penalizing Local Predictive Powercited by 1,010
  8. 2017Deeper, Broader and Artier Domain Generalizationcited by 983
  9. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 762
  10. 2013Domain Generalization via Invariant Feature Representationcited by 622
  11. 2018Generalizing to Unseen Domains via Adversarial Data Augmentationcited by 451
  12. 2019Domain Generalization by Solving Jigsaw Puzzlescited by 449
10 more
  1. 2020Self-Challenging Improves Cross-Domain Generalizationcited by 426
  2. 2017Unified Deep Supervised Domain Adaptation and Generalizationcited by 322
  3. 2016Domain Separation Networkscited by 317
  4. 2019Adversarial Domain Adaptation with Domain Mixupcited by 250
  5. 2019Episodic Training for Domain Generalizationcited by 245
  6. 2020Deep Domain-Adversarial Image Generation for Domain Generalisationcited by 231
  7. 2019Domain Generalization Using a Mixture of Multiple Latent Domainscited by 170
  8. 2018Domain Generalization with Domain-Specific Aggregation Modulescited by 61
  9. 2019Self-supervised Domain Adaptation for Computer Vision Taskscited by 58
  10. 2020One-Shot Unsupervised Cross-Domain Detectioncited by 19

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 6; 2023: 4; 2024: 3; 2025: 2; 2026: 1.

26 papers.

Sort:

By area:

  1. 2021Domain Generalization: A Surveycited by 760
  2. 2022Prompt Vision Transformer for Domain Generalizationcited by 52
  3. 2021Domain Prompt Learning for Efficiently Adapting CLIP to Unseen Domainscited by 39
  4. 2022Domain Generalization by Learning and Removing Domain-specific Featurescited by 28
  5. 2021Variational Disentanglement for Domain Generalizationcited by 18
  6. 2023Towards Artificial General Intelligence (AGI) in the Internet of Things (IoT): Opportunities and Challengescited by 14
  7. 2021Towards Data-Free Domain Generalizationcited by 11
  8. 2022A diverse large-scale building dataset and a novel plug-and-play domain generalization method for building extractioncited by 10
  9. 2023What Is Missing in IRM Training and Evaluation? Challenges and Solutionscited by 10
  10. 2025Gradient-Guided Annealing for Domain Generalizationcited by 9
  11. 2021Closer Look at the Uncertainty Estimation in Semantic Segmentation under Distributional Shiftcited by 8
  12. 2022Normalization Perturbation: A Simple Domain Generalization Method for Real-World Domain Shiftscited by 8
14 more
  1. 2023Moderately Distributional Exploration for Domain Generalizationcited by 8
  2. 2024FDS: Feedback-guided Domain Synthesis with Multi-Source Conditional Diffusion Models for Domain Generalizationcited by 5
  3. 2021Reappraising Domain Generalization in Neural Networkscited by 3
  4. 2022Conditional entropy minimization principle for learning domain invariant representation featurescited by 3
  5. 2021PLACE dropout: A Progressive Layer-wise and Channel-wise Dropout for Domain Generalizationcited by 2
  6. 2021Barycentric-alignment and reconstruction loss minimization for domain generalizationcited by 1
  7. 2021Discovery of New Multi-Level Features for Domain Generalization via Knowledge Corruptioncited by 1
  8. 2021Exploring Data Aggregation and Transformations to Generalize across Visual Domainscited by 0
  9. 2022Contrastive Learning for Cross-Domain Open World Recognitioncited by 0
  10. 2023Fairness meets Cross-Domain Learning: a new perspective on Models and Metricscited by 0
  11. 2024Adaptive Feature Fusion Neural Network for Glaucoma Segmentation on Unseen Fundus Imagescited by 0
  12. 2024TSynD: Targeted Synthetic Data Generation for Enhanced Medical Image Classificationcited by 0
  13. 2025Domain Generalization of Pathological Image Segmentation by Patch-Level and WSI-Level Contrastive Learningcited by 0
  14. 2026Evaluation of Randomization through Style Transfer for Enhanced Domain Generalizationcited by 0