You are here

Investigating Class-level Difficulty Factors in Multi-label Classification Problems


Mark Marsden, Kevin McGuinness, Joseph Antony, Haolin Wei, Milan Redzic, Jian Tang, Zhilan Hu, Alan Smeaton, Noel O'Connor

Publication Type: 
Refereed Conference Meeting Proceeding
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.
Conference Name: 
IEEE International Conference on Multimedia & Expo 2020 (ICME 2020)
Digital Object Identifer (DOI): 
Publication Date: 
Conference Location: 
United Kingdom (excluding Northern Ireland)
Dublin City University (DCU)
Open access repository: 
Publication document: