KS(conf ): A Light-Weight Test if a ConvNet Operates Outside of Its Specifications
This addresses quality control for computer vision systems in real-world applications by providing a lightweight, deployable method to warn users of potential performance drops due to distribution shifts.
The paper tackles the problem of detecting when a convolutional neural network operates on data outside its training distribution, proposing KS(conf) which uses a Kolmogorov-Smirnov test on confidence values to reliably identify such out-of-specs situations in experiments with ImageNet, AwA2, and DAVIS datasets.
Computer vision systems for automatic image categorization have become accurate and reliable enough that they can run continuously for days or even years as components of real-world commercial applications. A major open problem in this context, however, is quality control. Good classification performance can only be expected if systems run under the specific conditions, in particular data distributions, that they were trained for. Surprisingly, none of the currently used deep network architectures has a built-in functionality that could detect if a network operates on data from a distribution that it was not trained for and potentially trigger a warning to the human users. In this work, we describe KS(conf), a procedure for detecting such outside of the specifications operation. Building on statistical insights, its main step is the applications of a classical Kolmogorov-Smirnov test to the distribution of predicted confidence values. We show by extensive experiments using ImageNet, AwA2 and DAVIS data on a variety of ConvNets architectures that KS(conf) reliably detects out-of-specs situations. It furthermore has a number of properties that make it an excellent candidate for practical deployment: it is easy to implement, adds almost no overhead to the system, works with all networks, including pretrained ones, and requires no a priori knowledge about how the data distribution could change.