Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2310.17455 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913369636732928 |
|---|---|
| author | Tan, Zhiquan Zheng, Kaipeng Huang, Weiran |
| author_facet | Tan, Zhiquan Zheng, Kaipeng Huang, Weiran |
| contents | Semi-supervised learning has made remarkable strides by effectively utilizing a limited amount of labeled data while capitalizing on the abundant information present in unlabeled data. However, current algorithms often prioritize aligning image predictions with specific classes generated through self-training techniques, thereby neglecting the inherent relationships that exist within these classes. In this paper, we present a new approach called OTMatch, which leverages semantic relationships among classes by employing an optimal transport loss function to match distributions. We conduct experiments on many standard vision and language datasets. The empirical results show improvements in our method above baseline, this demonstrates the effectiveness and superiority of our approach in harnessing semantic relationships to enhance learning performance in a semi-supervised setting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_17455 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | OTMatch: Improving Semi-Supervised Learning with Optimal Transport Tan, Zhiquan Zheng, Kaipeng Huang, Weiran Computer Vision and Pattern Recognition Semi-supervised learning has made remarkable strides by effectively utilizing a limited amount of labeled data while capitalizing on the abundant information present in unlabeled data. However, current algorithms often prioritize aligning image predictions with specific classes generated through self-training techniques, thereby neglecting the inherent relationships that exist within these classes. In this paper, we present a new approach called OTMatch, which leverages semantic relationships among classes by employing an optimal transport loss function to match distributions. We conduct experiments on many standard vision and language datasets. The empirical results show improvements in our method above baseline, this demonstrates the effectiveness and superiority of our approach in harnessing semantic relationships to enhance learning performance in a semi-supervised setting. |
| title | OTMatch: Improving Semi-Supervised Learning with Optimal Transport |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2310.17455 |