KS(conf ): A Light-Weight Test if a ConvNet Operates Outside of Its Specifications

TL;DR

KS(conf) is a simple, efficient statistical test that detects when a ConvNet operates outside its trained data distribution, enhancing quality control in real-world vision applications.

Contribution

The paper introduces KS(conf), a novel, lightweight out-of-distribution detection method based on the Kolmogorov-Smirnov test applied to confidence scores.

Findings

KS(conf) reliably detects out-of-specs operation across multiple datasets.

It is easy to implement and adds minimal computational overhead.

Works with all ConvNet architectures, including pretrained models.

Abstract

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.