64 citations · 65 across the 5 of their papers we have counts for
5 papers
Improved Belief-Attention in Vision Task
Guoqiang Zhang
Recently, Belief-Attention \cite{Guoqiang25BeliefAttention} has been proposed by first performing an orthogonal projection of the softmax-based weighted summation of vectors wi…
On Suppressing Range of Adaptive Stepsizes of Adam to Improve Generalisation Performance
Guoqiang Zhang
A number of recent adaptive optimizers improve the generalisation performance of Adam by essentially reducing the variance of adaptive stepsizes to get closer to SGD with momentum.…
Advanced Dropout: A Model-free Methodology for Bayesian Dropout Optimization
Jiyang Xie, Zhanyu Ma, and Jianjun Lei +4
Due to lack of data, overfitting ubiquitously exists in real-world applications of deep neural networks (DNNs). We propose advanced dropout, a model-free methodology, to mitigate o…
GPCA: A Probabilistic Framework for Gaussian Process Embedded Channel Attention
Jiyang Xie, Dongliang Chang, Zhanyu Ma +2
Channel attention mechanisms have been commonly applied in many visual tasks for effective performance improvement. It is able to reinforce the informative channels as well as to s…
BALSON: Bayesian Least Squares Optimization with Nonnegative L1-Norm Constraint
Jiyang Xie, Zhanyu Ma, Guoqiang Zhang +4
A Bayesian approach termed BAyesian Least Squares Optimization with Nonnegative L1-norm constraint (BALSON) is proposed. The error distribution of data fitting is described by Gaus…