SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applications
Document Type
Conference Proceeding
Publication Title
Proceedings of the IEEE International Conference on Computer Vision
Abstract
Self-attention has become a defacto choice for capturing global context in various vision applications. However, its quadratic computational complexity with respect to image resolution limits its use in real-time applications, especially for deployment on resource-constrained mobile devices. Although hybrid approaches have been proposed to combine the advantages of convolutions and self-attention for a better speed-accuracy trade-off, the expensive matrix multiplication operations in self-attention remain a bottleneck. In this work, we introduce a novel efficient additive attention mechanism that effectively replaces the quadratic matrix multiplication operations with linear element-wise multiplications. Our design shows that the key-value interaction can be replaced with a linear layer without sacrificing any accuracy. Unlike previous state-of-the-art methods, our efficient formulation of self-attention enables its usage at all stages of the network. Using our proposed efficient additive attention, we build a series of models called "SwiftFormer"which achieves state-of-the-art performance in terms of both accuracy and mobile inference speed. Our small variant achieves 78.5% top-1 ImageNet-1K accuracy with only 0.8 ms latency on iPhone 14, which is more accurate and 2× faster compared to MobileViT-v2. Our code and models: https://tinyurl.com/5ft8v46w
First Page
17379
Last Page
17390
DOI
10.1109/ICCV51070.2023.01598
Publication Date
1-1-2023
Recommended Citation
A. Youssief et al., "SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applications," Proceedings of the IEEE International Conference on Computer Vision, pp. 17379 - 17390, Jan 2023.
The definitive version is available at https://doi.org/10.1109/ICCV51070.2023.01598