20.500.12556/RUL-128744 Cognitive relevance transform for population re-targeting 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. cognitive relevance deep learning crowd-sourcing target user population categorization classification kognitivna relevanca globoko učenje množično pridobivanje podatkov populacija ciljnih uporabnikov kategorizacija razvrščanje true false true Angleški jezik Slovenski jezik Članek v reviji 2021-07-27 10:57:45 2021-07-27 10:57:46 2022-09-07 04:16:57 0000-00-00 00:00:00 2020 0 0 36 str. iss. 17, art. 4668 Vol. 20 Sep.-1 2020 0000-00-00 Zaloznikova Objavljeno NiDoloceno 0000-00-00 0000-00-00 2020-08-19 004.8 1424-8220 10.3390/s20174668 38147075 RAZ_Koporec_Gregor_2020.pdf RAZ_Koporec_Gregor_2020.pdf 1 1D2312F63E75E7BA2E24308A4E6992FA 4133081b26f74e2923c8e411582e3d6c1289f09bac345b131026666bb6e0dc53 5c92691b-eeb9-11eb-a523-00155dcfd717 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=145589 https://www.mdpi.com/1424-8220/20/17/4668 1 8b414a57-eeb8-11eb-a523-00155dcfd717 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=145588 Fakulteta za elektrotehniko 0 0 0