# Unsupervised Cross-domain Image Classification by Distance Metric Guided Feature Alignment

arXiv: https://arxiv.org/abs/2008.08433 · HTML: https://mlsanity.com/paper/2008.08433/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Aug 2020.

## Built on by (most cited first, 5 of 5)

- [A Review on Deep-Learning Algorithms for Fetal Ultrasound-Image Analysis](https://mlsanity.com/paper/2201.12260/) (2022)
- [Emergent Discrete Communication in Semantic Spaces](https://mlsanity.com/paper/2108.01828/) (2021)
- [Embracing the Disharmony in Medical Imaging: A Simple and Effective Framework for Domain Adaptation](https://mlsanity.com/paper/2103.12857/) (2021)
- [A Systematic Review of Generalization Research in Medical Image Classification](https://mlsanity.com/paper/2403.12167/) (2024)
- [Efficient Feature Extraction Using Light-Weight CNN Attention-Based Deep Learning Architectures for Ultrasound Fetal Plane Classification](https://mlsanity.com/paper/2410.17396/) (2024)

## Abstract (arXiv)

Learning deep neural networks that are generalizable across different domains remains a challenge due to the problem of domain shift. Unsupervised domain adaptation is a promising avenue which transfers knowledge from a source domain to a target domain without using any labels in the target domain. Contemporary techniques focus on extracting domain-invariant features using domain adversarial training. However, these techniques neglect to learn discriminative class boundaries in the latent representation space on a target domain and yield limited adaptation performance. To address this problem, we propose distance metric guided feature alignment (MetFA) to extract discriminative as well as domain-invariant features on both source and target domains. The proposed MetFA method explicitly and directly learns the latent representation without using domain adversarial training. Our model integrates class distribution alignment to transfer semantic knowledge from a source domain to a target domain. We evaluate the proposed method on fetal ultrasound datasets for cross-device image classification. Experimental results demonstrate that the proposed method outperforms the state-of-the-art and enables model generalization.