# Improving Transferability of Domain Adaptation Networks Through Domain Alignment Layers

arXiv: https://arxiv.org/abs/2109.02693 · HTML: https://mlsanity.com/paper/2109.02693/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 30 references that are in the map.
- First posted on arXiv 6 Sep 2021.

## Builds on (most cited first, 18 of 18)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1705.00609/) (2017)
- [Deep Cocktail Network: Multi-source Unsupervised Domain Adaptation with Category Shift](https://mlsanity.com/paper/1803.00830/) (2018)
- [AutoDIAL: Automatic DomaIn Alignment Layers](https://mlsanity.com/paper/1704.08082/) (2017)
- [Multi-source Distilling Domain Adaptation](https://mlsanity.com/paper/1911.11554/) (2019)
- [On the Effectiveness of Image Rotation for Open Set Domain Adaptation](https://mlsanity.com/paper/2007.12360/) (2020)
- [Domain Aggregation Networks for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1909.05352/) (2019)
- [MADAN: Multi-source Adversarial Domain Aggregation Network for Domain Adaptation](https://mlsanity.com/paper/2003.00820/) (2020)
- [Inferring Latent Domains for Unsupervised Deep Domain Adaptation](https://mlsanity.com/paper/2103.13873/) (2021)
- [Just DIAL: DomaIn Alignment Layers for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1702.06332/) (2017)
- [Faster and Accurate Compressed Video Action Recognition Straight from the Frequency Domain](https://mlsanity.com/paper/2012.13726/) (2020)

## Built on by (most cited first, 4 of 4)

- [Tightening Classification Boundaries in Open Set Domain Adaptation through Unknown Exploitation](https://mlsanity.com/paper/2309.08964/) (2023)
- [Mixup-based Deep Metric Learning Approaches for Incomplete Supervision](https://mlsanity.com/paper/2204.13572/) (2022)
- [Beyond the Known: Enhancing Open Set Domain Adaptation with Unknown Exploration](https://mlsanity.com/paper/2412.18105/) (2024)
- [E-MLNet: Enhanced Mutual Learning for Universal Domain Adaptation with Sample-Specific Weighting](https://mlsanity.com/paper/2509.09006/) (2025)

## Abstract (arXiv)

Deep learning (DL) has been the primary approach used in various computer vision tasks due to its relevant results achieved on many tasks. However, on real-world scenarios with partially or no labeled data, DL methods are also prone to the well-known domain shift problem. Multi-source unsupervised domain adaptation (MSDA) aims at learning a predictor for an unlabeled domain by assigning weak knowledge from a bag of source models. However, most works conduct domain adaptation leveraging only the extracted features and reducing their domain shift from the perspective of loss function designs. In this paper, we argue that it is not sufficient to handle domain shift only based on domain-level features, but it is also essential to align such information on the feature space. Unlike previous works, we focus on the network design and propose to embed Multi-Source version of DomaIn Alignment Layers (MS-DIAL) at different levels of the predictor. These layers are designed to match the feature distributions between different domains and can be easily applied to various MSDA methods. To show the robustness of our approach, we conducted an extensive experimental evaluation considering two challenging scenarios: digit recognition and object classification. The experimental results indicated that our approach can improve state-of-the-art MSDA methods, yielding relative gains of up to +30.64% on their classification accuracies.