27 citations · 31 across the 3 of their papers we have counts for
3 papers
cs.CV2022★ 2 cited
Restructurable Activation Networks
Kartikeya Bhardwaj, James Ward, Caleb Tung +6
Is it possible to restructure the non-linear activation functions in a deep network to create hardware-efficient models? To address this question, we propose a new paradigm called…
cs.CV2021★ 2 cited
Armour: Generalizable Compact Self-Attention for Vision Transformers
Lingchuan Meng
Attention-based transformer networks have demonstrated promising potential as their applications extend from natural language processing to vision. However, despite the recent impr…
cs.NE2019★ 27 cited
Efficient Winograd Convolution via Integer Arithmetic
Lingchuan Meng, John Brothers
Convolution is the core operation for many deep neural networks. The Winograd convolution algorithms have been shown to accelerate the widely-used small convolution sizes. Quantize…