# Soft-Masked Semi-Dual Optimal Transport for Partial Domain Adaptation

arXiv: https://arxiv.org/abs/2505.01664 · HTML: https://mlsanity.com/paper/2505.01664/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 50 references that are in the map.
- First posted on arXiv 3 May 2025.

## Builds on (most cited first, 26 of 26)

- [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)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [Deep Transfer Learning with Joint Adaptation Networks](https://mlsanity.com/paper/1605.06636/) (2016)
- [Optimal Transport for Domain Adaptation](https://mlsanity.com/paper/1507.00504/) (2015)
- [VisDA: The Visual Domain Adaptation Challenge](https://mlsanity.com/paper/1710.06924/) (2017)
- [Joint Distribution Optimal Transportation for Domain Adaptation](https://mlsanity.com/paper/1705.08848/) (2017)
- [DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1803.10081/) (2018)
- [Stochastic Optimization for Large-scale Optimal Transport](https://mlsanity.com/paper/1605.08527/) (2016)
- [Generate To Adapt: Aligning Domains using Generative Adversarial Networks](https://mlsanity.com/paper/1704.01705/) (2017)
- [Partial Adversarial Domain Adaptation](https://mlsanity.com/paper/1808.04205/) (2018)
- [Unbalanced minibatch Optimal Transport; applications to Domain Adaptation](https://mlsanity.com/paper/2103.03606/) (2021)
- [Theoretical Analysis of Domain Adaptation with Optimal Transport](https://mlsanity.com/paper/1610.04420/) (2016)
- [Importance Weighted Adversarial Nets for Partial Domain Adaptation](https://mlsanity.com/paper/1803.09210/) (2018)
- [Partial Transfer Learning with Selective Adversarial Networks](https://mlsanity.com/paper/1707.07901/) (2017)
- [Deep Residual Correction Network for Partial Domain Adaptation](https://mlsanity.com/paper/2004.04914/) (2020)
- [Improving Mini-batch Optimal Transport via Partial Transportation](https://mlsanity.com/paper/2108.09645/) (2021)
- [Unsupervised Domain Adaptation via Discriminative Manifold Propagation](https://mlsanity.com/paper/2008.10030/) (2020)
- [Unbalanced Optimal Transport through Non-negative Penalized Linear Regression](https://mlsanity.com/paper/2106.04145/) (2021)
- [Domain Adversarial Reinforcement Learning for Partial Domain Adaptation](https://mlsanity.com/paper/1905.04094/) (2019)
- [Learning Target Domain Specific Classifier for Partial Domain Adaptation](https://mlsanity.com/paper/2008.10785/) (2020)
- [Selective Transfer with Reinforced Transfer Network for Partial Domain Adaptation](https://mlsanity.com/paper/1905.10756/) (2019)
- [Improved Techniques for Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1809.03625/) (2018)

## Abstract (arXiv)

Visual domain adaptation aims to learn discriminative and domain-invariant representation for an unlabeled target domain by leveraging knowledge from a labeled source domain. Partial domain adaptation (PDA) is a general and practical scenario in which the target label space is a subset of the source one. The challenges of PDA exist due to not only domain shift but also the non-identical label spaces of domains. In this paper, a Soft-masked Semi-dual Optimal Transport (SSOT) method is proposed to deal with the PDA problem. Specifically, the class weights of domains are estimated, and then a reweighed source domain is constructed, which is favorable in conducting class-conditional distribution matching with the target domain. A soft-masked transport distance matrix is constructed by category predictions, which will enhance the class-oriented representation ability of optimal transport in the shared feature space. To deal with large-scale optimal transport problems, the semi-dual formulation of the entropy-regularized Kantorovich problem is employed since it can be optimized by gradient-based algorithms. Further, a neural network is exploited to approximate the Kantorovich potential due to its strong fitting ability. This network parametrization also allows the generalization of the dual variable outside the supports of the input distribution. The SSOT model is built upon neural networks, which can be optimized alternately in an end-to-end manner. Extensive experiments are conducted on four benchmark datasets to demonstrate the effectiveness of SSOT.