Description
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.
Papers Using This Method
Systemic risk mitigation in supply chains through network rewiring2025-04-17Supply chain network rewiring dynamics at the firm-level2025-03-26Inventory Consensus Control in Supply Chain Networks using Dissipativity-Based Control and Topology Co-Design2025-02-10Kernel Stochastic Configuration Networks for Nonlinear Regression2024-12-08Deeper Insights into Learning Performance of Stochastic Configuration Networks2024-11-13Teeth Localization and Lesion Segmentation in CBCT Images using SpatialConfiguration-Net and U-Net2023-12-19Estimating the impact of supply chain network contagion on financial stability2023-05-04Closed-form control with spike coding networks2022-12-25A structurally informed model for modulating functional connectivity2022-08-24Spherical Channels for Modeling Atomic Interactions2022-06-29Orthogonal Stochastic Configuration Networks with Adaptive Construction Parameter for Data Analytics2022-05-26New methods of removing debris and high-throughput counting of cyst nematode eggs extracted from field soil2022-05-25Robotic agricultural instrument for automated extraction of nematode cysts and eggs from soil to improve integrated pest management2022-05-24A New Learning Paradigm for Stochastic Configuration Network: SCN+2022-03-11Can the clocks tick together despite the noise? Stochastic simulations and analysis2022-02-24Sequential convolutional network for behavioral pattern extraction in gait recognition2021-04-23Nonlinear computations in spiking neural networks through multiplicative synapses2020-09-08Suppressing Uncertainties for Large-Scale Facial Expression Recognition2020-02-24