Confidence Scoring Using Whitebox Meta-models with Linear Classifier Probes

We propose a confidence scoring mechanism for multi-layer neural networks based on a paradigm of a base model and a meta-model. The confidence score is learned by the meta-model using features derived from the base model -- a deep multi-layer neural network -- considered a whitebox. As features, we investigate linear classifier probes inserted between the various layers of the base model and trained using each layer's intermediate activations. Experiments show that this approach outperforms various baselines in a filtering task, i.e., task of rejecting samples with low confidence. Experimental results are presented using CIFAR-10 and CIFAR-100 dataset with and without added noise exploring various aspects of the method.