Self-Cure Network (SCN)

Self-Cure Network, or SCN, is a method for suppressing uncertainties for large-scale facial expression recognition, prventing deep networks from overfitting uncertain facial images. Specifically, SCN suppresses the uncertainty from two different aspects: 1) a self-attention mechanism over mini-batch to weight each training sample with a ranking regularization, and 2) a careful relabeling mechanism to modify the labels of these samples in the lowest-ranked group.
相关学科: SRNNCardiac SegmentationFPNYOLOXKeyword SpottingMulti-target regressionConversational SearchFCNInception ModuleResNeXt

学科讨论

讨论Icon

暂无讨论内容,你可以

推荐文献

按被引用数

学科管理组

暂无学科课代表,你可以申请成为课代表

重要学者

Jie Zhang

193659 被引用,5433 篇论文

Raymond J. Dolan

133426 被引用,1043 篇论文

Edward T. Bullmore

124130 被引用,850 篇论文

Rui Zhang

93872 被引用,2747 篇论文

Ruslan Salakhutdinov

89393 被引用,413 篇论文

Peter B. Jones

87151 被引用,2361 篇论文

Qiang Yang

59434 被引用,1165 篇论文

Robert W. Heath

55976 被引用,1028 篇论文

Allan L. Reiss

55046 被引用,557 篇论文

Peter Fonagy

52686 被引用,1281 篇论文