SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applications
This addresses the need for efficient transformer-based models for real-time mobile vision applications, offering a novel solution to a known bottleneck.
The paper tackles the problem of self-attention's quadratic computational complexity limiting real-time vision applications on mobile devices by introducing an efficient additive attention mechanism that replaces matrix multiplications with linear operations, resulting in a model achieving 78.5% top-1 ImageNet-1K accuracy with 0.8 ms latency on iPhone 14, which is more accurate and 2x faster than MobileViT-v2.
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 2x faster compared to MobileViT-v2. Code: https://github.com/Amshaker/SwiftFormer