Data to 7 Oct 2026

Generalizing to Unseen Domains via Adversarial Data Augmentation

arXiv 1805.12018 ↗First posted 30 May 2018cs.CVcited by 451

Not on the map. Why?

Abstract (arXiv)

We are concerned with learning models that generalize well to different unseen domains. We consider a worst-case formulation over data distributions that are near the source domain in the feature space. Only using training data from a single source distribution, we propose an iterative procedure that augments the dataset with examples from a fictitious target domain that is "hard" under the current model. We show that our iterative scheme is an adaptive data augmentation method where we append adversarial examples at each iteration. For softmax losses, we show that our method is a data-dependent regularization scheme that behaves differently from classical regularizers that regularize towards zero (e.g., ridge or lasso). On digit recognition and semantic segmentation tasks, our method learns models improve performance across a range of a priori unknown target domains.

Key facts. Cited by 451 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 110; 2022: 89; 2023: 100; 2024: 69; 2025: 61; 2026: 22.

451 papers.

Sort:

By area:

2021Generalizing to Unseen Domains: A Survey on Domain Generalizationcited by 762
2021Domain Generalization: A Surveycited by 760
2023SmoothLLM: Defending Large Language Models Against Jailbreaking Attackscited by 434
2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
2021A Fourier-based Framework for Domain Generalizationcited by 287
2021FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Spacecited by 284
2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 276
2022Improving Out-of-Distribution Robustness via Selective Augmentationcited by 202
2022Parameter-free Online Test-time Adaptationcited by 184
2021Learning to Diversify for Single Domain Generalizationcited by 170
2021FSDR: Frequency Space Domain Randomization for Domain Generalizationcited by 163
2021Deep Stable Learning for Out-Of-Distribution Generalizationcited by 153

38 more

2022SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptationcited by 146
2022Causality Inspired Representation Learning for Domain Generalizationcited by 136
2021MSeg: A Composite Dataset for Multi-domain Semantic Segmentationcited by 122
2022Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalizationcited by 122
2021Causality-inspired Single-source Domain Generalization for Medical Image Segmentationcited by 118
2021Open Domain Generalization with Domain-Augmented Meta-Learningcited by 115
2021Model-Based Domain Generalizationcited by 103
2021Progressive Domain Expansion Network for Single Domain Generalizationcited by 96
2023CLIPood: Generalizing CLIP to Out-of-Distributionscited by 96
2021Towards Principled Disentanglement for Domain Generalizationcited by 91
2021AugMax: Adversarial Composition of Random Augmentations for Robust Trainingcited by 89
2023CLIP the Gap: A Single Domain Generalization Approach for Object Detectioncited by 87
2021OoD-Bench: Quantifying and Understanding Two Dimensions of Out-of-Distribution Generalizationcited by 86
2022NICO++: Towards Better Benchmarking for Domain Generalizationcited by 86
2021Adversarially Adaptive Normalization for Single Domain Generalizationcited by 85
2021Delving Deep into the Generalization of Vision Transformers under Distribution Shiftscited by 85
2021Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD Generalizationcited by 83
2021Generalizable Person Re-identification with Relevance-aware Mixture of Expertscited by 77
2021On the effectiveness of adversarial training against common corruptionscited by 71
2022Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentationcited by 69
2022Improving Test-Time Adaptation via Shift-agnostic Weight Regularization and Nearest Source Prototypescited by 67
2021Improved OOD Generalization via Adversarial Training and Pre-trainingcited by 66
2021Cross-Domain Few-Shot Classification via Adversarial Task Augmentationcited by 63
2021Domain Generalization via Gradient Surgerycited by 60
2021MetaAlign: Coordinating Domain Alignment and Classification for Unsupervised Domain Adaptationcited by 54
2022DrugOOD: Out-of-Distribution (OOD) Dataset Curator and Benchmark for AI-aided Drug Discovery -- A Focus on Affinity Prediction Problems with Noise Annotationscited by 54
2021Boosting the Generalization Capability in Cross-Domain Few-shot Learning via Noise-enhanced Supervised Autoencodercited by 51
2021Test-time Batch Statistics Calibration for Covariate Shiftcited by 50
2022Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-of-Expertscited by 50
2021RDA: Robust Domain Adaptation via Fourier Adversarial Attackingcited by 48
2021Style Normalization and Restitution for Domain Generalization and Adaptationcited by 46
2021Domain Adversarial Neural Networks for Domain Generalization: When It Works and How to Improvecited by 46
2021Generalizable Cross-modality Medical Image Segmentation via Style Augmentation and Dual Normalizationcited by 45
2022Out-of-distribution Generalization with Causal Invariant Transformationscited by 45
2021Semi-Supervised Domain Generalization with Stochastic StyleMatchcited by 43
20213D-VField: Adversarial Augmentation of Point Clouds for Domain Generalization in 3D Object Detectioncited by 43
2022Harnessing Out-Of-Distribution Examples via Augmenting Content and Stylecited by 43
2023Meta-causal Learning for Single Domain Generalizationcited by 43

50 most cited of 451 All 451 (JSON)