KS(conf): A light-weight test if a multiclass classifier operates outside of its specifications

R. Sun, C. Lampert, International Journal of Computer Vision (2019).

Download
OA 3.37 MB

Journal Article | Epub ahead of print | English
Author
Department
Abstract
We study the problem of automatically detecting if a given multi-class classifier operates outside of its specifications (out-of-specs), i.e. on input data from a different distribution than what it was trained for. This is an important problem to solve on the road towards creating reliable computer vision systems for real-world applications, because the quality of a classifier’s predictions cannot be guaranteed if it operates out-of-specs. Previously proposed methods for out-of-specs detection make decisions on the level of single inputs. This, however, is insufficient to achieve low false positive rate and high false negative rates at the same time. In this work, we describe a new procedure named KS(conf), based on statistical reasoning. Its main component is a classical Kolmogorov–Smirnov test that is applied to the set of predicted confidence values for batches of samples. Working with batches instead of single samples allows increasing the true positive rate without negatively affecting the false positive rate, thereby overcoming a crucial limitation of single sample tests. We show by extensive experiments using a variety of convolutional network architectures and datasets that KS(conf) reliably detects out-of-specs situations even under conditions where other tests fail. 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 any classifier that outputs confidence scores, and requires no a priori knowledge about how the data distribution could change.
Publishing Year
Date Published
2019-10-10
Journal Title
International Journal of Computer Vision
ISSN
eISSN
IST-REx-ID

Cite this

Sun R, Lampert C. KS(conf): A light-weight test if a multiclass classifier operates outside of its specifications. International Journal of Computer Vision. 2019. doi:10.1007/s11263-019-01232-x
Sun, R., & Lampert, C. (2019). KS(conf): A light-weight test if a multiclass classifier operates outside of its specifications. International Journal of Computer Vision. https://doi.org/10.1007/s11263-019-01232-x
Sun, Rémy, and Christoph Lampert. “KS(Conf): A Light-Weight Test If a Multiclass Classifier Operates Outside of Its Specifications.” International Journal of Computer Vision, 2019. https://doi.org/10.1007/s11263-019-01232-x.
R. Sun and C. Lampert, “KS(conf): A light-weight test if a multiclass classifier operates outside of its specifications,” International Journal of Computer Vision, 2019.
Sun R, Lampert C. 2019. KS(conf): A light-weight test if a multiclass classifier operates outside of its specifications. International Journal of Computer Vision.
Sun, Rémy, and Christoph Lampert. “KS(Conf): A Light-Weight Test If a Multiclass Classifier Operates Outside of Its Specifications.” International Journal of Computer Vision, Springer Nature, 2019, doi:10.1007/s11263-019-01232-x.
All files available under the following license(s):
Creative Commons License:
CC-BYCreative Commons Attribution 4.0 International Public License (CC-BY 4.0)
Main File(s)
File Name
Access Level
OA Open Access
Last Uploaded
2019-10-14T09:16:47Z


Export

Marked Publications

Open Data IST Research Explorer

Search this title in

Google Scholar