Журнал «Современная Наука»

Russian (CIS)English (United Kingdom)
 MOSCOW +7(495)-142-86-81

METHODS FOR EVALUATING INTERPRETATIONS OF COMPUTER VISION MODELS

Kapustin Ilia Sergeevich  (RANEPA, Moscow, Russia Moscow, Russia)

Romashkova Oxana Nikolaevna  (Doctor of Engineering, Professor, Russian Presidential Academy of National Economy and Public Administration (RANEPA), Moscow, Russia )

The article examines the problem of interpretability of computer vision models. The author notes that although there are many methods designed to explain the decisions made by deep neural networks, little effort has been made to ensure that these explanations are objectively relevant. The article proves the correlation between the quality of a model and the quality of its interpretation, considers metrics for assessing interpretations taken from the field of algorithmic stability: average generalization (MeGe) and relative consistency (ReCo), and also proposes a new metric for assessing the quality of interpretations of computer vision models, taking into account quality of the original model.

Keywords:interpretation, machine learning, correlation, MeGe, ReCo, interpretation quality, model evaluation
 

Read the full article …

Citation link:
Kapustin I. S., Romashkova O. N. METHODS FOR EVALUATING INTERPRETATIONS OF COMPUTER VISION MODELS // Современная наука: актуальные проблемы теории и практики. Серия: Естественные и Технические Науки. -2024. -№01/2. -С. 29-35 DOI 10.37882/2223-2966.2024.1-2.05
LEGAL INFORMATION:
Reproduction of materials is permitted only for non-commercial purposes with reference to the original publication. Protected by the laws of the Russian Federation. Any violations of the law are prosecuted.
© ООО "Научные технологии"

Terms Publications

Issues of the journals (Archive)

ECONOMICS AND LAW
HUMANITIES
NATURAL AND TECHNICAL SCIENCES
COGNITION

Серия - Natural and Technical Sciences