Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2308.15081 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929727729565696 |
|---|---|
| author | Zhao, Hengwei Wang, Xinyu Li, Jingtao Zhong, Yanfei |
| author_facet | Zhao, Hengwei Wang, Xinyu Li, Jingtao Zhong, Yanfei |
| contents | Positive-unlabeled learning (PU learning) in hyperspectral remote sensing imagery (HSI) is aimed at learning a binary classifier from positive and unlabeled data, which has broad prospects in various earth vision applications. However, when PU learning meets limited labeled HSI, the unlabeled data may dominate the optimization process, which makes the neural networks overfit the unlabeled data. In this paper, a Taylor variational loss is proposed for HSI PU learning, which reduces the weight of the gradient of the unlabeled data by Taylor series expansion to enable the network to find a balance between overfitting and underfitting. In addition, the self-calibrated optimization strategy is designed to stabilize the training process. Experiments on 7 benchmark datasets (21 tasks in total) validate the effectiveness of the proposed method. Code is at: https://github.com/Hengwei-Zhao96/T-HOneCls. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2308_15081 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Class Prior-Free Positive-Unlabeled Learning with Taylor Variational Loss for Hyperspectral Remote Sensing Imagery Zhao, Hengwei Wang, Xinyu Li, Jingtao Zhong, Yanfei Computer Vision and Pattern Recognition Positive-unlabeled learning (PU learning) in hyperspectral remote sensing imagery (HSI) is aimed at learning a binary classifier from positive and unlabeled data, which has broad prospects in various earth vision applications. However, when PU learning meets limited labeled HSI, the unlabeled data may dominate the optimization process, which makes the neural networks overfit the unlabeled data. In this paper, a Taylor variational loss is proposed for HSI PU learning, which reduces the weight of the gradient of the unlabeled data by Taylor series expansion to enable the network to find a balance between overfitting and underfitting. In addition, the self-calibrated optimization strategy is designed to stabilize the training process. Experiments on 7 benchmark datasets (21 tasks in total) validate the effectiveness of the proposed method. Code is at: https://github.com/Hengwei-Zhao96/T-HOneCls. |
| title | Class Prior-Free Positive-Unlabeled Learning with Taylor Variational Loss for Hyperspectral Remote Sensing Imagery |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2308.15081 |