# Semantic Data Augmentation based Distance Metric Learning for Domain Generalization

arXiv: https://arxiv.org/abs/2208.02803 · HTML: https://mlsanity.com/paper/2208.02803/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 68 references that are in the map.
- First posted on arXiv 2 Aug 2022.

## Builds on (most cited first, 30 of 43)

- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [Deeper, Broader and Artier Domain Generalization](https://mlsanity.com/paper/1710.03077/) (2017)
- [Domain Generalization via Invariant Feature Representation](https://mlsanity.com/paper/1301.2115/) (2013)
- [Domain Generalization with MixStyle](https://mlsanity.com/paper/2104.02008/) (2021)
- [Domain Generalization by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1903.06864/) (2019)
- [Deep Metric Learning via Lifted Structured Feature Embedding](https://mlsanity.com/paper/1511.06452/) (2015)
- [Efficient Processing of Deep Neural Networks: A Tutorial and Survey](https://mlsanity.com/paper/1703.09039/) (2017)
- [Self-Challenging Improves Cross-Domain Generalization](https://mlsanity.com/paper/2007.02454/) (2020)
- [Domain Generalization via Model-Agnostic Learning of Semantic Features](https://mlsanity.com/paper/1910.13580/) (2019)
- [Return of Frustratingly Easy Domain Adaptation](https://mlsanity.com/paper/1511.05547/) (2015)
- [Methods for Interpreting and Understanding Deep Neural Networks](https://mlsanity.com/paper/1706.07979/) (2017)
- [Semi-supervised Domain Adaptation via Minimax Entropy](https://mlsanity.com/paper/1904.06487/) (2019)
- [Unified Deep Supervised Domain Adaptation and Generalization](https://mlsanity.com/paper/1709.10190/) (2017)
- [Learning to Learn Single Domain Generalization](https://mlsanity.com/paper/2003.13216/) (2020)
- [Learning to Generate Novel Domains for Domain Generalization](https://mlsanity.com/paper/2007.03304/) (2020)
- [A Fourier-based Framework for Domain Generalization](https://mlsanity.com/paper/2105.11120/) (2021)
- [Generalizing Across Domains via Cross-Gradient Training](https://mlsanity.com/paper/1804.10745/) (2018)
- [Domain Generalization for Object Recognition with Multi-task Autoencoders](https://mlsanity.com/paper/1508.07680/) (2015)
- [Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Data](https://mlsanity.com/paper/1909.00889/) (2019)
- [Episodic Training for Domain Generalization](https://mlsanity.com/paper/1902.00113/) (2019)
- [Deep Domain-Adversarial Image Generation for Domain Generalisation](https://mlsanity.com/paper/2003.06054/) (2020)
- [Domain Generalization using Causal Matching](https://mlsanity.com/paper/2006.07500/) (2020)
- [Progressive Feature Alignment for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1811.08585/) (2018)
- [Domain Generalization Using a Mixture of Multiple Latent Domains](https://mlsanity.com/paper/1911.07661/) (2019)
- [SoftTriple Loss: Deep Metric Learning Without Triplet Sampling](https://mlsanity.com/paper/1909.05235/) (2019)
- [Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentation](https://mlsanity.com/paper/2003.00867/) (2020)
- [Robust and Generalizable Visual Representation Learning via Random Convolutions](https://mlsanity.com/paper/2007.13003/) (2020)

## Built on by (most cited first, 11 of 11)

- [DGMamba: Domain Generalization via Generalized State Space Model](https://mlsanity.com/paper/2404.07794/) (2024)
- [Leveraging Large Language Models for Relevance Judgments in Legal Case Retrieval](https://mlsanity.com/paper/2403.18405/) (2024)
- [Diverse Target and Contribution Scheduling for Domain Generalization](https://mlsanity.com/paper/2309.16460/) (2023)
- [ProS: Prompting-to-simulate Generalized knowledge for Universal Cross-Domain Retrieval](https://mlsanity.com/paper/2312.12478/) (2023)
- [BSDA: Bayesian Random Semantic Data Augmentation for Medical Image Classification](https://mlsanity.com/paper/2403.06138/) (2024)
- [Resolve Domain Conflicts for Generalizable Remote Physiological Measurement](https://mlsanity.com/paper/2404.07855/) (2024)
- [Domain Generalization via Discrete Codebook Learning](https://mlsanity.com/paper/2504.06572/) (2025)
- [Let Synthetic Data Shine: Domain Reassembly and Soft-Fusion for Single Domain Generalization](https://mlsanity.com/paper/2503.13617/) (2025)
- [FEDTAIL: Federated Long-Tailed Domain Generalization with Sharpness-Guided Gradient Matching](https://mlsanity.com/paper/2506.08518/) (2025)
- [Beyond Seen Bounds: Class-Centric Polarization for Single-Domain Generalized Deep Metric Learning](https://mlsanity.com/paper/2601.09121/) (2026)
- [CouCE: A Unified Causal Framework for Debiased Deep Metric Learning](https://mlsanity.com/paper/2606.30365/) (2026)

## Abstract (arXiv)

Domain generalization (DG) aims to learn a model on one or more different but related source domains that could be generalized into an unseen target domain. Existing DG methods try to prompt the diversity of source domains for the model's generalization ability, while they may have to introduce auxiliary networks or striking computational costs. On the contrary, this work applies the implicit semantic augmentation in feature space to capture the diversity of source domains. Concretely, an additional loss function of distance metric learning (DML) is included to optimize the local geometry of data distribution. Besides, the logits from cross entropy loss with infinite augmentations is adopted as input features for the DML loss in lieu of the deep features. We also provide a theoretical analysis to show that the logits can approximate the distances defined on original features well. Further, we provide an in-depth analysis of the mechanism and rational behind our approach, which gives us a better understanding of why leverage logits in lieu of features can help domain generalization. The proposed DML loss with the implicit augmentation is incorporated into a recent DG method, that is, Fourier Augmented Co-Teacher framework (FACT). Meanwhile, our method also can be easily plugged into various DG methods. Extensive experiments on three benchmarks (Digits-DG, PACS and Office-Home) have demonstrated that the proposed method is able to achieve the state-of-the-art performance.