cosFormer: Rethinking Softmax In Attention.

Zhen Qin Weixuan Sun Hui Deng Dongxu Li Yunshen Wei Baohong Lv Junjie Yan Lingpeng Kong Yiran Zhong

Published in: ICLR (2022)

Keyphrases

neural network
machine learning
image sequences
bayesian networks
multiscale
preprocessing
multiresolution
visual attention
activation function
hidden nodes