DeVIT：基于差分计算的低功耗视觉Transformer加速方法
DeVIT: Low-Power Vision Transformer Acceleration Using Delta Computation
浏览论文内容
中文总结 AI 辅助
针对视觉Transformer在资源受限设备上部署的高复杂度问题，本文提出DeVIT方法，通过量化引入的值局部性，利用差分计算实现无乘法器的矩阵乘法，以实现低功耗加速。
中文摘要 AI 辅助
基于Transformer的深度学习模型已在各领域展现出前所未有的性能，尤其在自然语言处理和计算机视觉领域表现突出。然而，这类模型因计算复杂度高、内存规模及带宽需求大，在资源受限设备上部署面临重大挑战。为降低内存使用并提升效率，研究者采用低比特模型权重。量化除减少处理和内存需求外，还引入了值局部性特性：极大量参数被限制在有限的数值范围内。为充分利用该局部性，本文提出DeVIT，一种用于视觉Transformer的加速方法，利用差分计算实现无乘法器的矩阵乘法。
英文摘要
The emergence of transformer-based deep learning models has brought unprecedented performance across various domains, particularly in natural language processing and computer vision. However, deploying these models, especially on resource-constrained devices, poses significant challenges due to their high computational complexity and large memory size and bandwidth requirements. This complexity has led researchers to use low-bit model weights to reduce memory usage and improve efficiency. In addition to reducing processing and memory demands, quantization introduces another useful property: value locality, where the extremely large number of parameters are restricted to a limited range of values. To fully take advantage of this locality, this paper presents DeVIT, an acceleration method for vision transformers that leverages differential computation to enable multiplier-less matrix multiplication.
