Regularization

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.

Source: Suppressing Uncertainties for Large-Scale Facial Expression Recognition

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Management 1 20.00%
Incremental Learning 1 20.00%
Gait Recognition 1 20.00%
Time Series 1 20.00%
Facial Expression Recognition 1 20.00%

Components


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories