Confidence from Invariance to Image Transformations

Understand

We develop a technique for automatically detecting the classification errors of a pre-trained visual classifier.

• Our method is agnostic to the form of the classifier, requiring access only to classifier responses to a set of inputs.
• We train a parametric binary classifier (error/correct) on a representation derived from a set of classifier responses generated from multiple copies of the same input, each subject to a different natural image transformation.
• Thus, we establish a measure of confidence in classifier's decision by analyzing the invariance of its decision under various transformations.