Cognitive relevance transform for population re-targeting

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

Povzetek

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.

Ključne besede

kognitivna relevanca;globoko učenje;množično pridobivanje podatkov;populacija ciljnih uporabnikov;kategorizacija;razvrščanje;cognitive relevance;deep learning;crowd-sourcing;target user population;categorization;classification;

Podatki

Jezik:	Angleški jezik
Leto izida:	2020
Tipologija:	1.01 - Izvirni znanstveni članek
Organizacija:	UL FE - Fakulteta za elektrotehniko
UDK:	004.8
COBISS:	38147075
ISSN:	1424-8220
Št. ogledov:	249
Št. prenosov:	88
Ocena:	0 (0 glasov)
Metapodatki:

Ostali podatki

Sekundarni jezik:	Slovenski jezik
Sekundarne ključne besede:	kognitivna relevanca;globoko učenje;množično pridobivanje podatkov;populacija ciljnih uporabnikov;kategorizacija;razvrščanje;
Vrsta dela (COBISS):	Članek v reviji
Strani:	str. 1-36
Letnik:	ǂiss. ǂ17
Zvezek:	4668
Čas izdaje:	Sep.-1 2020
DOI:	10.3390/s20174668
ID:	13181170