Re-Thinking Classification Confidence with Model Quality Quantification
Yancheng Pan,Huijing Zhao,Yancheng Pan,Huijing Zhao
Deep neural networks using for real-world classification task require high reliability and robustness. However, the Softmax output by the last layer of network is often over-confident. We propose a novel confidence estimation method by considering model quality for deep classification models. Two metrics, MQ-Repres and MQ-Discri are developed accordingly to evaluate the model quality, and also pro...
