# Robust Domain-Free Domain Generalization with Class-aware Alignment

arXiv: https://arxiv.org/abs/2102.08897 · HTML: https://mlsanity.com/paper/2102.08897/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 36 references that are in the map.
- First posted on arXiv 17 Feb 2021.

## Builds on (most cited first, 21 of 21)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [SmoothGrad: removing noise by adding noise](https://mlsanity.com/paper/1706.03825/) (2017)
- [Learning to Generalize: Meta-Learning for Domain Generalization](https://mlsanity.com/paper/1710.03463/) (2017)
- [Out-of-Distribution Generalization via Risk Extrapolation (REx)](https://mlsanity.com/paper/2003.00688/) (2020)
- [Generalizing to Unseen Domains via Adversarial Data Augmentation](https://mlsanity.com/paper/1805.12018/) (2018)
- [Domain Generalization by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1903.06864/) (2019)
- [Self-Challenging Improves Cross-Domain Generalization](https://mlsanity.com/paper/2007.02454/) (2020)
- [Contrastive Adaptation Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1901.00976/) (2019)
- [Domain Generalization via Model-Agnostic Learning of Semantic Features](https://mlsanity.com/paper/1910.13580/) (2019)
- [Unified Deep Supervised Domain Adaptation and Generalization](https://mlsanity.com/paper/1709.10190/) (2017)
- [Episodic Training for Domain Generalization](https://mlsanity.com/paper/1902.00113/) (2019)
- [Domain Generalization Using a Mixture of Multiple Latent Domains](https://mlsanity.com/paper/1911.07661/) (2019)
- [Learning Robust Representations by Projecting Superficial Statistics Out](https://mlsanity.com/paper/1903.06256/) (2019)
- [Generalizing to unseen domains via distribution matching](https://mlsanity.com/paper/1911.00804/) (2019)
- [Best sources forward: domain generalization through source-specific nets](https://mlsanity.com/paper/1806.05810/) (2018)
- [Multi-Source Deep Domain Adaptation with Weak Supervision for Time-Series Sensor Data](https://mlsanity.com/paper/2005.10996/) (2020)
- [Domain Generalization with Domain-Specific Aggregation Modules](https://mlsanity.com/paper/1809.10966/) (2018)
- [Frustratingly Simple Domain Generalization via Image Stylization](https://mlsanity.com/paper/2006.11207/) (2020)
- [Unsupervised Domain Adaptation via Regularized Conditional Alignment](https://mlsanity.com/paper/1905.10885/) (2019)
- [Improving Cross-Corpus Speech Emotion Recognition with Adversarial Discriminative Domain Generalization (ADDoG)](https://mlsanity.com/paper/1903.12094/) (2019)

## Built on by (most cited first, 6 of 6)

- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [Out-of-Distribution Representation Learning for Time Series Classification](https://mlsanity.com/paper/2209.07027/) (2022)
- [DIVERSIFY: A General Framework for Time Series Out-of-distribution Detection and Generalization](https://mlsanity.com/paper/2308.02282/) (2023)
- [Tri-Level Navigator: LLM-Empowered Tri-Level Learning for Time Series OOD Generalization](https://mlsanity.com/paper/2410.07018/) (2024)
- [Critically examining the Domain Generalizability of Facial Expression Recognition models](https://mlsanity.com/paper/2106.15453/) (2021)
- [Domain Generalization via Selective Consistency Regularization for Time Series Classification](https://mlsanity.com/paper/2206.07876/) (2022)

## Abstract (arXiv)

While deep neural networks demonstrate state-of-the-art performance on a variety of learning tasks, their performance relies on the assumption that train and test distributions are the same, which may not hold in real-world applications. Domain generalization addresses this issue by employing multiple source domains to build robust models that can generalize to unseen target domains subject to shifts in data distribution. In this paper, we propose Domain-Free Domain Generalization (DFDG), a model-agnostic method to achieve better generalization performance on the unseen test domain without the need for source domain labels. DFDG uses novel strategies to learn domain-invariant class-discriminative features. It aligns class relationships of samples through class-conditional soft labels, and uses saliency maps, traditionally developed for post-hoc analysis of image classification networks, to remove superficial observations from training inputs. DFDG obtains competitive performance on both time series sensor and image classification public datasets.