Maximally Separated Active Learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913586255757312 |
|---|---|
| author | Kasarla, Tejaswi Jha, Abhishek Tervoort, Faye Cucchiara, Rita Mettes, Pascal |
| author_facet | Kasarla, Tejaswi Jha, Abhishek Tervoort, Faye Cucchiara, Rita Mettes, Pascal |
| contents | Active Learning aims to optimize performance while minimizing annotation costs by selecting the most informative samples from an unlabelled pool. Traditional uncertainty sampling often leads to sampling bias by choosing similar uncertain samples. We propose an active learning method that utilizes fixed equiangular hyperspherical points as class prototypes, ensuring consistent inter-class separation and robust feature representations. Our approach introduces Maximally Separated Active Learning (MSAL) for uncertainty sampling and a combined strategy (MSAL-D) for incorporating diversity. This method eliminates the need for costly clustering steps, while maintaining diversity through hyperspherical uniformity. We demonstrate strong performance over existing active learning techniques across five benchmark datasets, highlighting the method's effectiveness and integration ease. The code is available on GitHub. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_17444 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Maximally Separated Active Learning Kasarla, Tejaswi Jha, Abhishek Tervoort, Faye Cucchiara, Rita Mettes, Pascal Machine Learning Active Learning aims to optimize performance while minimizing annotation costs by selecting the most informative samples from an unlabelled pool. Traditional uncertainty sampling often leads to sampling bias by choosing similar uncertain samples. We propose an active learning method that utilizes fixed equiangular hyperspherical points as class prototypes, ensuring consistent inter-class separation and robust feature representations. Our approach introduces Maximally Separated Active Learning (MSAL) for uncertainty sampling and a combined strategy (MSAL-D) for incorporating diversity. This method eliminates the need for costly clustering steps, while maintaining diversity through hyperspherical uniformity. We demonstrate strong performance over existing active learning techniques across five benchmark datasets, highlighting the method's effectiveness and integration ease. The code is available on GitHub. |
| title | Maximally Separated Active Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2411.17444 |