| Naslov: | Fostering fairness in image classification through awareness of sensitive data |
|---|
| Avtorji: | ID Colakovic, Ivona (Avtor)
ID Karakatič, Sašo (Avtor) |
|---|
| Datoteke: |  1-s2.0-S1568494625004016-main.pdf (2,01 MB)
MD5: 131792810C6ABE1A402EC5820F6B701B
 https://www.sciencedirect.com/science/article/pii/S1568494625004016?via%3Dihub#sec3
|
|---|
| Jezik: | Angleški jezik |
|---|
| Vrsta gradiva: | Članek v reviji |
|---|
| Tipologija: | 1.01 - Izvirni znanstveni članek |
|---|
| Organizacija: | FERI - Fakulteta za elektrotehniko, računalništvo in informatiko
|
|---|
| Opis: | Machine learning (ML) has demonstrated remarkable ability to uncover hidden patterns in data. However, the presence of biases and discrimination originating from the data itself and, consequently, emerging in the ML outcomes, remains a pressing concern. With the exponential growth of unstructured data, such as images, fairness has become increasingly critical, as neural network (NN) models may inadvertently learn and perpetuate societal and historical biases. To address this challenge, we propose a fairness-aware loss function that iteratively prioritizes the worst-performing sensitive group during NN training. This approach aims to balance treatment quality across sensitive groups, achieving fairer image classification outcomes while incurring only a slight compromise in overall performance. Our method, evaluated on the FairFace dataset, demonstrates significant improvements in fairness metrics while maintaining comparable overall quality. These trade-offs highlight that the minor decrease in overall quality is justified by the improvement in fairness of the models. |
|---|
| Ključne besede: | fairness, search-basimage classification, machine learning, supervised learnign, neural networks |
|---|
| Status publikacije: | Objavljeno |
|---|
| Verzija publikacije: | Objavljena publikacija |
|---|
| Poslano v recenzijo: | 05.11.2024 |
|---|
| Datum sprejetja članka: | 22.03.2025 |
|---|
| Datum objave: | 04.04.2025 |
|---|
| Založnik: | Elsevier |
|---|
| Leto izida: | 2025 |
|---|
| Št. strani: | 10 str. |
|---|
| Številčenje: | Vol. 136, [article] no.] 113090 |
|---|
| PID: | 20.500.12556/DKUM-92602  |
|---|
| UDK: | 004.8 |
|---|
| COBISS.SI-ID: | 232495363 |
|---|
| DOI: | 10.1016/j.asoc.2025.113090 |
|---|
| ISSN pri članku: | 1872-9681 |
|---|
| Avtorske pravice: | © 2025 The Authors |
|---|
| Datum objave v DKUM: | 23.04.2025 |
|---|
| Število ogledov: | 345 |
|---|
| Število prenosov: | 11 |
|---|
| Metapodatki: |    |
|---|
| Področja: | Ostalo
|
|---|
|
:
|
Kopiraj citat |
|---|
| | | | Skupna ocena: | (0 glasov) |
|---|
| Vaša ocena: | Ocenjevanje je dovoljeno samo prijavljenim uporabnikom. |
|---|
| Objavi na: |  |
|---|
Postavite miškin kazalec na naslov za izpis povzetka. Klik na naslov izpiše
podrobnosti ali sproži prenos. |
