Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2412.18027 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915078095241216 |
|---|---|
| author | Neiterman, Evgeny Hershkovitch Ben-Artzi, Gil |
| author_facet | Neiterman, Evgeny Hershkovitch Ben-Artzi, Gil |
| contents | Training very deep convolutional networks is challenging, requiring significant computational resources and time. Existing acceleration methods often depend on specific architectures or require network modifications. We introduce LayerDropBack (LDB), a simple yet effective method to accelerate training across a wide range of deep networks. LDB introduces randomness only in the backward pass, maintaining the integrity of the forward pass, guaranteeing that the same network is used during both training and inference. LDB can be seamlessly integrated into the training process of any model without altering its architecture, making it suitable for various network topologies. Our extensive experiments across multiple architectures (ViT, Swin Transformer, EfficientNet, DLA) and datasets (CIFAR-100, ImageNet) show significant training time reductions of 16.93\% to 23.97\%, while preserving or even enhancing model accuracy. Code is available at \url{https://github.com/neiterman21/LDB}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_18027 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LayerDropBack: A Universally Applicable Approach for Accelerating Training of Deep Networks Neiterman, Evgeny Hershkovitch Ben-Artzi, Gil Computer Vision and Pattern Recognition Training very deep convolutional networks is challenging, requiring significant computational resources and time. Existing acceleration methods often depend on specific architectures or require network modifications. We introduce LayerDropBack (LDB), a simple yet effective method to accelerate training across a wide range of deep networks. LDB introduces randomness only in the backward pass, maintaining the integrity of the forward pass, guaranteeing that the same network is used during both training and inference. LDB can be seamlessly integrated into the training process of any model without altering its architecture, making it suitable for various network topologies. Our extensive experiments across multiple architectures (ViT, Swin Transformer, EfficientNet, DLA) and datasets (CIFAR-100, ImageNet) show significant training time reductions of 16.93\% to 23.97\%, while preserving or even enhancing model accuracy. Code is available at \url{https://github.com/neiterman21/LDB}. |
| title | LayerDropBack: A Universally Applicable Approach for Accelerating Training of Deep Networks |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.18027 |