FasterViT: Fast Vision Transformers with Hierarchical Attention
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917627795865600 |
|---|---|
| author | Hatamizadeh, Ali Heinrich, Greg Yin, Hongxu Tao, Andrew Alvarez, Jose M. Kautz, Jan Molchanov, Pavlo |
| author_facet | Hatamizadeh, Ali Heinrich, Greg Yin, Hongxu Tao, Andrew Alvarez, Jose M. Kautz, Jan Molchanov, Pavlo |
| contents | We design a new family of hybrid CNN-ViT neural networks, named FasterViT, with a focus on high image throughput for computer vision (CV) applications. FasterViT combines the benefits of fast local representation learning in CNNs and global modeling properties in ViT. Our newly introduced Hierarchical Attention (HAT) approach decomposes global self-attention with quadratic complexity into a multi-level attention with reduced computational costs. We benefit from efficient window-based self-attention. Each window has access to dedicated carrier tokens that participate in local and global representation learning. At a high level, global self-attentions enable the efficient cross-window communication at lower costs. FasterViT achieves a SOTA Pareto-front in terms of accuracy and image throughput. We have extensively validated its effectiveness on various CV tasks including classification, object detection and segmentation. We also show that HAT can be used as a plug-and-play module for existing networks and enhance them. We further demonstrate significantly faster and more accurate performance than competitive counterparts for images with high resolution. Code is available at https://github.com/NVlabs/FasterViT. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_06189 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | FasterViT: Fast Vision Transformers with Hierarchical Attention Hatamizadeh, Ali Heinrich, Greg Yin, Hongxu Tao, Andrew Alvarez, Jose M. Kautz, Jan Molchanov, Pavlo Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning We design a new family of hybrid CNN-ViT neural networks, named FasterViT, with a focus on high image throughput for computer vision (CV) applications. FasterViT combines the benefits of fast local representation learning in CNNs and global modeling properties in ViT. Our newly introduced Hierarchical Attention (HAT) approach decomposes global self-attention with quadratic complexity into a multi-level attention with reduced computational costs. We benefit from efficient window-based self-attention. Each window has access to dedicated carrier tokens that participate in local and global representation learning. At a high level, global self-attentions enable the efficient cross-window communication at lower costs. FasterViT achieves a SOTA Pareto-front in terms of accuracy and image throughput. We have extensively validated its effectiveness on various CV tasks including classification, object detection and segmentation. We also show that HAT can be used as a plug-and-play module for existing networks and enhance them. We further demonstrate significantly faster and more accurate performance than competitive counterparts for images with high resolution. Code is available at https://github.com/NVlabs/FasterViT. |
| title | FasterViT: Fast Vision Transformers with Hierarchical Attention |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2306.06189 |