Fast Fishing: Approximating BAIT for Efficient and Scalable Deep Active Image Classification
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_ | 1866918382177091584 |
|---|---|
| author | Huseljic, Denis Hahn, Paul Herde, Marek Rauch, Lukas Sick, Bernhard |
| author_facet | Huseljic, Denis Hahn, Paul Herde, Marek Rauch, Lukas Sick, Bernhard |
| contents | Deep active learning (AL) seeks to minimize the annotation costs for training deep neural networks. BAIT, a recently proposed AL strategy based on the Fisher Information, has demonstrated impressive performance across various datasets. However, BAIT's high computational and memory requirements hinder its applicability on large-scale classification tasks, resulting in current research neglecting BAIT in their evaluation. This paper introduces two methods to enhance BAIT's computational efficiency and scalability. Notably, we significantly reduce its time complexity by approximating the Fisher Information. In particular, we adapt the original formulation by i) taking the expectation over the most probable classes, and ii) constructing a binary classification task, leading to an alternative likelihood for gradient computations. Consequently, this allows the efficient use of BAIT on large-scale datasets, including ImageNet. Our unified and comprehensive evaluation across a variety of datasets demonstrates that our approximations achieve strong performance with considerably reduced time complexity. Furthermore, we provide an extensive open-source toolbox that implements recent state-of-the-art AL strategies, available at https://github.com/dhuseljic/dal-toolbox. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_08981 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Fast Fishing: Approximating BAIT for Efficient and Scalable Deep Active Image Classification Huseljic, Denis Hahn, Paul Herde, Marek Rauch, Lukas Sick, Bernhard Computer Vision and Pattern Recognition Machine Learning Deep active learning (AL) seeks to minimize the annotation costs for training deep neural networks. BAIT, a recently proposed AL strategy based on the Fisher Information, has demonstrated impressive performance across various datasets. However, BAIT's high computational and memory requirements hinder its applicability on large-scale classification tasks, resulting in current research neglecting BAIT in their evaluation. This paper introduces two methods to enhance BAIT's computational efficiency and scalability. Notably, we significantly reduce its time complexity by approximating the Fisher Information. In particular, we adapt the original formulation by i) taking the expectation over the most probable classes, and ii) constructing a binary classification task, leading to an alternative likelihood for gradient computations. Consequently, this allows the efficient use of BAIT on large-scale datasets, including ImageNet. Our unified and comprehensive evaluation across a variety of datasets demonstrates that our approximations achieve strong performance with considerably reduced time complexity. Furthermore, we provide an extensive open-source toolbox that implements recent state-of-the-art AL strategies, available at https://github.com/dhuseljic/dal-toolbox. |
| title | Fast Fishing: Approximating BAIT for Efficient and Scalable Deep Active Image Classification |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2404.08981 |