A Class-aware Optimal Transport Approach with Higher-Order Moment Matching for Unsupervised Domain Adaptation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929226578395136 |
|---|---|
| author | Nguyen, Tuan Nguyen, Van Le, Trung Zhao, He Tran, Quan Hung Phung, Dinh |
| author_facet | Nguyen, Tuan Nguyen, Van Le, Trung Zhao, He Tran, Quan Hung Phung, Dinh |
| contents | Unsupervised domain adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. In this paper, we introduce a novel approach called class-aware optimal transport (OT), which measures the OT distance between a distribution over the source class-conditional distributions and a mixture of source and target data distribution. Our class-aware OT leverages a cost function that determines the matching extent between a given data example and a source class-conditional distribution. By optimizing this cost function, we find the optimal matching between target examples and source class-conditional distributions, effectively addressing the data and label shifts that occur between the two domains. To handle the class-aware OT efficiently, we propose an amortization solution that employs deep neural networks to formulate the transportation probabilities and the cost function. Additionally, we propose minimizing class-aware Higher-order Moment Matching (HMM) to align the corresponding class regions on the source and target domains. The class-aware HMM component offers an economical computational approach for accurately evaluating the HMM distance between the two distributions. Extensive experiments on benchmark datasets demonstrate that our proposed method significantly outperforms existing state-of-the-art baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_15952 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Class-aware Optimal Transport Approach with Higher-Order Moment Matching for Unsupervised Domain Adaptation Nguyen, Tuan Nguyen, Van Le, Trung Zhao, He Tran, Quan Hung Phung, Dinh Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Unsupervised domain adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. In this paper, we introduce a novel approach called class-aware optimal transport (OT), which measures the OT distance between a distribution over the source class-conditional distributions and a mixture of source and target data distribution. Our class-aware OT leverages a cost function that determines the matching extent between a given data example and a source class-conditional distribution. By optimizing this cost function, we find the optimal matching between target examples and source class-conditional distributions, effectively addressing the data and label shifts that occur between the two domains. To handle the class-aware OT efficiently, we propose an amortization solution that employs deep neural networks to formulate the transportation probabilities and the cost function. Additionally, we propose minimizing class-aware Higher-order Moment Matching (HMM) to align the corresponding class regions on the source and target domains. The class-aware HMM component offers an economical computational approach for accurately evaluating the HMM distance between the two distributions. Extensive experiments on benchmark datasets demonstrate that our proposed method significantly outperforms existing state-of-the-art baselines. |
| title | A Class-aware Optimal Transport Approach with Higher-Order Moment Matching for Unsupervised Domain Adaptation |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.15952 |