# Feature Alignment and Restoration for Domain Generalization and Adaptation

arXiv: https://arxiv.org/abs/2006.12009 · HTML: https://mlsanity.com/paper/2006.12009/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jun 2020.

## Built on by (most cited first, 30 of 31)

- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Deep Stable Learning for Out-Of-Distribution Generalization](https://mlsanity.com/paper/2104.07876/) (2021)
- [Domain Prompt Learning for Efficiently Adapting CLIP to Unseen Domains](https://mlsanity.com/paper/2111.12853/) (2021)
- [Anomaly Detection under Distribution Shift](https://mlsanity.com/paper/2303.13845/) (2023)
- [ToAlign: Task-oriented Alignment for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2106.10812/) (2021)
- [Intra-Source Style Augmentation for Improved Domain Generalization](https://mlsanity.com/paper/2210.10175/) (2022)
- [Towards Artificial General Intelligence (AGI) in the Internet of Things (IoT): Opportunities and Challenges](https://mlsanity.com/paper/2309.07438/) (2023)
- [Re-energizing Domain Discriminator with Sample Relabeling for Adversarial Domain Adaptation](https://mlsanity.com/paper/2103.11661/) (2021)
- [Learning Domain Invariant Representations in Goal-conditioned Block MDPs](https://mlsanity.com/paper/2110.14248/) (2021)
- [Cross-domain few-shot learning with unlabelled data](https://mlsanity.com/paper/2101.07899/) (2021)
- [Confounder Identification-free Causal Visual Feature Learning](https://mlsanity.com/paper/2111.13420/) (2021)
- [Intra- & Extra-Source Exemplar-Based Style Synthesis for Improved Domain Generalization](https://mlsanity.com/paper/2307.00648/) (2023)
- [Learning Fair Invariant Representations under Covariate and Correlation Shifts Simultaneously](https://mlsanity.com/paper/2408.09312/) (2024)
- [StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization](https://mlsanity.com/paper/2406.00275/) (2024)
- [INSURE: An Information Theory Inspired Disentanglement and Purification Model for Domain Generalization](https://mlsanity.com/paper/2309.04063/) (2023)
- [Relating tSNE and UMAP to Classical Dimensionality Reduction](https://mlsanity.com/paper/2306.11898/) (2023)
- [Mitigate Domain Shift by Primary-Auxiliary Objectives Association for Generalizing Person ReID](https://mlsanity.com/paper/2310.15913/) (2023)
- [Feature-Distribution Perturbation and Calibration for Generalized Person ReID](https://mlsanity.com/paper/2205.11197/) (2022)
- [Joint covariate-alignment and concept-alignment: a framework for domain generalization](https://mlsanity.com/paper/2208.00898/) (2022)
- [Learning to Augment via Implicit Differentiation for Domain Generalization](https://mlsanity.com/paper/2210.14271/) (2022)
- [Explainability-aided Domain Generalization for Image Classification](https://mlsanity.com/paper/2104.01742/) (2021)
- [Trade-off between reconstruction loss and feature alignment for domain generalization](https://mlsanity.com/paper/2210.15000/) (2022)
- [Group-wise Scaling and Orthogonal Decomposition for Domain-Invariant Feature Extraction in Face Anti-Spoofing](https://mlsanity.com/paper/2507.04006/) (2025)
- [Frequency Decomposition to Tap the Potential of Single Domain for Generalization](https://mlsanity.com/paper/2304.07261/) (2023)
- [Improving Intrusion Detection with Domain-Invariant Representation Learning in Latent Space](https://mlsanity.com/paper/2312.17300/) (2023)
- [SynthGenNet: a self-supervised approach for test-time generalization using synthetic multi-source domain mixing of street view images](https://mlsanity.com/paper/2509.02287/) (2025)
- [Token-Based Detection of Spurious Correlations in Vision Transformers](https://mlsanity.com/paper/2509.04009/) (2025)
- [SemAlign: Language Guided Semi-supervised Domain Generalization](https://mlsanity.com/paper/2601.11724/) (2026)
- [A Multi-directional Meta-Learning Framework for Class-Generalizable Anomaly Detection](https://mlsanity.com/paper/2601.19833/) (2026)

## Abstract (arXiv)

For domain generalization (DG) and unsupervised domain adaptation (UDA), cross domain feature alignment has been widely explored to pull the feature distributions of different domains in order to learn domain-invariant representations. However, the feature alignment is in general task-ignorant and could result in degradation of the discrimination power of the feature representation and thus hinders the high performance. In this paper, we propose a unified framework termed Feature Alignment and Restoration (FAR) to simultaneously ensure high generalization and discrimination power of the networks for effective DG and UDA. Specifically, we perform feature alignment (FA) across domains by aligning the moments of the distributions of attentively selected features to reduce their discrepancy. To ensure high discrimination, we propose a Feature Restoration (FR) operation to distill task-relevant features from the residual information and use them to compensate for the aligned features. For better disentanglement, we enforce a dual ranking entropy loss constraint in the FR step to encourage the separation of task-relevant and task-irrelevant features. Extensive experiments on multiple classification benchmarks demonstrate the high performance and strong generalization of our FAR framework for both domain generalization and unsupervised domain adaptation.