mlsanityData to 14 Oct 2026

Free Lunch for Domain Adversarial Training: Environment Label Smoothing

arXiv 2302.00194 ↗First posted 1 Feb 2023cs.LGcited by 33

Not on the map. Why?

Abstract (arXiv)

A fundamental challenge for machine learning models is how to generalize learned models for out-of-distribution (OOD) data. Among various approaches, exploiting invariant features by Domain Adversarial Training (DAT) received widespread attention. Despite its success, we observe training instability from DAT, mostly due to over-confident domain discriminator and environment label noise. To address this issue, we proposed Environment Label Smoothing (ELS), which encourages the discriminator to output soft probability, which thus reduces the confidence of the discriminator and alleviates the impact of noisy environment labels. We demonstrate, both experimentally and theoretically, that ELS can improve training stability, local convergence, and robustness to noisy environment labels. By incorporating ELS with DAT methods, we are able to yield state-of-art results on a wide range of domain generalization/adaptation tasks, particularly when the environment labels are highly noisy.

Key facts. Cited by 33 papers in the map (data through 14 Oct 2026). Builds on 66 of its 100 references that are in the map. First posted on arXiv 1 Feb 2023.

Builds on

66 of 100 references.

References · 66

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  3. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
  4. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  5. 2018How Powerful are Graph Neural Networks?cited by 4,393
  6. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  7. 2016Improved Techniques for Training GANscited by 2,970
  8. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  9. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,218
  10. 2020Shortcut Learning in Deep Neural Networkscited by 1,969
  11. 2019Invariant Risk Minimizationcited by 1,854
  12. 2015Spatial Transformer Networkscited by 1,429
38 more
  1. 2020WILDS: A Benchmark of in-the-Wild Distribution Shiftscited by 1,375
  2. 2017Adversarial Discriminative Domain Adaptationcited by 1,311
  3. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,247
  4. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,200
  5. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,188
  6. 2020In Search of Lost Domain Generalizationcited by 1,054
  7. 2017Deeper, Broader and Artier Domain Generalizationcited by 986
  8. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 763
  9. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 742
  10. 2018Which Training Methods for GANs do actually Converge?cited by 679
  11. 2013Domain Generalization via Invariant Feature Representationcited by 623
  12. 2016f-GAN: Training Generative Neural Samplers using Variational Divergence Minimizationcited by 506
  13. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 464
  14. 2019Bridging Theory and Algorithm for Domain Adaptationcited by 332
  15. 2020Environment Inference for Invariant Learningcited by 306
  16. 2016NIPS 2016 Tutorial: Generative Adversarial Networkscited by 285
  17. 2017Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitrocited by 281
  18. 2020Gradient Starvation: A Learning Proclivity in Neural Networkscited by 267
  19. 2017MMD GAN: Towards Deeper Understanding of Moment Matching Networkcited by 254
  20. 2015Domain Generalization for Object Recognition with Multi-task Autoencoderscited by 253
  21. 2021Fishr: Invariant Gradient Variances for Out-of-Distribution Generalizationcited by 186
  22. 2020Adaptive Risk Minimization: Learning to Adapt to Domain Shiftcited by 183
  23. 2017Domain Generalization by Marginal Transfer Learningcited by 180
  24. 2017Generalization and Equilibrium in Generative Adversarial Nets (GANs)cited by 166
  25. 2019NLNL: Negative Learning for Noisy Labelscited by 151
  26. 2018A Variational Inequality Perspective on Generative Adversarial Networkscited by 144
  27. 2020Unsupervised Domain Adaptation via Structurally Regularized Deep Clusteringcited by 140
  28. 2017Stabilizing Training of Generative Adversarial Networks through Regularizationcited by 118
  29. 2019Generalizing to unseen domains via distribution matchingcited by 110
  30. 2017The Numerics of GANscited by 105
  31. 2021Towards Principled Disentanglement for Domain Generalizationcited by 91
  32. 2022A Closer Look at Smoothness in Domain Adversarial Trainingcited by 85
  33. 2021TVT: Transferable Vision Transformer for Unsupervised Domain Adaptationcited by 81
  34. 2020Meta Batch-Instance Normalization for Generalizable Person Re-Identificationcited by 77
  35. 2020Continuously Indexed Domain Adaptationcited by 75
  36. 2021To Smooth or Not? When Label Smoothing Meets Noisy Labelscited by 70
  37. 2016Amortised MAP Inference for Image Super-resolutioncited by 68
  38. 2017Gradient descent GAN optimization is locally stablecited by 67

50 most cited of 66 All 66 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 8; 2024: 15; 2025: 5; 2026: 5.

33 papers.

Sort:

By area:

  1. 2023OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensemblingcited by 74
  2. 2023AdaNPC: Exploring Non-Parametric Classifier for Test-Time Adaptationcited by 48
  3. 2024On the Out-Of-Distribution Generalization of Multimodal Large Language Modelscited by 30
  4. 2023Flatness-Aware Minimization for Domain Generalizationcited by 27
  5. 2024DGMamba: Domain Generalization via Generalized State Space Modelcited by 21
  6. 2025Does Unsupervised Domain Adaptation Improve the Robustness of Amortized Bayesian Inference? A Systematic Evaluationcited by 10
  7. 2023Domain-Guided Conditional Diffusion Model for Unsupervised Domain Adaptationcited by 9
  8. 2024NewTerm: Benchmarking Real-Time New Terms for Large Language Models with Annual Updatescited by 8
  9. 2023Improving Anomaly Segmentation with Multi-Granularity Cross-Domain Alignmentcited by 6
  10. 2024LogoRA: Local-Global Representation Alignment for Robust Time Series Classificationcited by 3
  11. 2024Identifiable Shared Component Analysis of Unpaired Multimodal Mixturescited by 3
  12. 2025Domain Generalization via Discrete Codebook Learningcited by 3
21 more
  1. 2025Variance Matters: Improving Domain Adaptation via Stratified Samplingcited by 3
  2. 2024VLLaVO: Mitigating Visual Gap through LLMscited by 2
  3. 2024Improving Fast Adversarial Training via Self-Knowledge Guidancecited by 2
  4. 2026Order Matters: Improving Domain Adaptation by Reordering Datacited by 2
  5. 2023Supervised Domain Adaptation for Recognizing Retinal Diseases from Wide-Field Fundus Imagescited by 1
  6. 2024Dual Teacher Knowledge Distillation with Domain Alignment for Face Anti-spoofingcited by 1
  7. 2024Learning Conditional Invariances through Non-Commutativitycited by 1
  8. 2024Stochastic Adversarial Networks for Multi-Domain Text Classificationcited by 1
  9. 2024Stable Heterogeneous Treatment Effect Estimation across Out-of-Distribution Populationscited by 1
  10. 2026VT-DUDA: Visual Token Conditioning for Diffusion-guided Unsupervised Domain Adaptationcited by 1
  11. 2023Diffusion-based Target Sampler for Unsupervised Domain Adaptationcited by 0
  12. 2023Domain Similarity-Perceived Label Assignment for Domain Generalized Underwater Object Detectioncited by 0
  13. 2024Cooperative Students: Navigating Unsupervised Domain Adaptation in Nighttime Object Detectioncited by 0
  14. 2024Gradually Vanishing Gap in Prototypical Network for Unsupervised Domain Adaptationcited by 0
  15. 2024Invariant Correlation of Representation with Label: Enhancing Domain Generalization in Noisy Environmentscited by 0
  16. 2024Guidance Not Obstruction: A Conjugate Consistent Enhanced Strategy for Domain Generalizationcited by 0
  17. 2025PCaM: A Progressive Focus Attention-Based Information Fusion Method for Improving Vision Transformer Domain Adaptationcited by 0
  18. 2025LLMs-based Augmentation for Domain Adaptation in Long-tailed Food Datasetscited by 0
  19. 2026Variance-reduced Domain Adaptation using Paired Samplingcited by 0
  20. 2026Online Variance Reduction for Domain Adaptation on Streaming Datacited by 0
  21. 2026Revisiting Diffusion Fine-Tuning for Unsupervised Domain Adaptationcited by 0