Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Investigating class-level difficulty factors in multi-label classification problems

Marsden, Mark, McGuinness, Kevin orcid logoORCID: 0000-0003-1336-6477, Antony, Joseph orcid logoORCID: 0000-0001-6493-7829, Wei, Haolin, Redzic, Milan, Tang, Jian, Hu, Zhilan, Smeaton, Alan F. orcid logoORCID: 0000-0003-1028-8389 and O'Connor, Noel E. orcid logoORCID: 0000-0002-4033-9135 (2020) Investigating class-level difficulty factors in multi-label classification problems. In: IEEE International Conference on Multimedia & Expo, 6 - 10 July 2020, London, UK. (Virtual).

Abstract
This work investigates the use of class-level difficulty factors in multi-label classification problems for the first time. Four class-level difficulty factors are proposed: frequency, visual variation, semantic abstraction, and class co-occurrence. Once computed for a given multi-label classification dataset, these difficulty factors are shown to have several potential applications including the prediction of class-level performance across datasets and the improvement of predictive performance through difficulty weighted optimisation. Significant improvements to mAP and AUC performance are observed for two challenging multi-label datasets (WWW Crowd and Visual Genome) with the inclusion of difficulty weighted optimisation. The proposed technique does not require any additional computational complexity during training or inference and can be extended over time with inclusion of other class-level difficulty factors.
Metadata
Item Type:Conference or Workshop Item (Paper)
Event Type:Conference
Refereed:Yes
Uncontrolled Keywords:Multi-label; difficulty factors; frequency; visual variation; semantic abstraction; class co-occurrence
Subjects:UNSPECIFIED
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
DCU Faculties and Schools > Faculty of Engineering and Computing > School of Electronic Engineering
Research Initiatives and Centres > INSIGHT Centre for Data Analytics
Published in: 2020 IEEE International Conference on Multimedia and Expo (ICME). . IEEE.
Publisher:IEEE
Official URL:http://dx.doi.org/10.1109/ICME46284.2020.9102798
Copyright Information:© 2020 The Authors
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
ID Code:24426
Deposited On:25 Jun 2020 15:55 by Joseph Antony . Last Modified 05 Jan 2022 17:08
Documents

Full text available as:

[thumbnail of ICME2020_CameraReady.pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
263kB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record