Cognitive relevance transform for population re-targeting

Koporec, Gregor (author), Košir, Andrej (author), Leonardis, Aleš (author), Perš, Janez (author)

This work examines the differences between a human and a machine in object recognition tasks. The machine is useful as much as the output classification labels are correct and match the dataset-provided labels. However, very often a discrepancy occurs because the dataset label is different than the one expected by a human. To correct this, the concept of the target user population is introduced. The paper presents a complete methodology for either adapting the output of a pre-trained, state-of-the-art object classification algorithm to the target population or inferring a proper, user-friendly categorization from the target population. The process is called ‘user population re-targeting’. The methodology includes a set of specially designed population tests, which provide crucial data about the categorization that the target population prefers. The transformation between the dataset-bound categorization and the new, population-specific categorization is called the ‘Cognitive Relevance Transform’. The results of the experiments on the well-known datasets have shown that the target population preferred such a transformed categorization by a large margin, that the performance of human observers is probably better than previously thought, and that the outcome of re-targeting may be difficult to predict without actual tests on the target population.

• Language: English
• Keywords: cognitive relevance, deep learning, crowd-sourcing, target user population, categorization, classification
• Work type: Article
• Typology: 1.01 - Original Scientific Article
• Organization: FE - Faculty of Electrical Engineering
• Publication status: Published
• Publication version: Version of Record
• Publication date: 19.08.2020
• Year: 2020
• Number of pages: 36 str.
• Numbering: Vol. 20, iss. 17, art. 4668
• PID: 20.500.12556/RUL-128744
• UDC: 004.8
• ISSN on article: 1424-8220
• DOI: 10.3390/s20174668
• COBISS.SI-ID: 38147075
• Publication date in RUL: 27.07.2021

Record is a part of a journal

• Title: Sensors
• Shortened title: Sensors
• Publisher: MDPI
• ISSN: 1424-8220
• COBISS.SI-ID: 10176278

Licences

• License: CC BY 4.0, Creative Commons Attribution 4.0 International
• Link: http://creativecommons.org/licenses/by/4.0/
• Description: This is the standard Creative Commons license that gives others maximum freedom to do what they want with the work as long as they credit the author.
• Licensing start date: 19.08.2020

Secondary language

• Language: Slovenian
• Keywords: kognitivna relevanca, globoko učenje, množično pridobivanje podatkov, populacija ciljnih uporabnikov, kategorizacija, razvrščanje