Prediction With Visual Evidence : Sketch Classification Explanation via Stroke-Level Attributions

Sketch classification models have been extensively investigated by designing a task-driven deep neural network. Despite their successful performances, few works have attempted to explain the prediction of sketch classifiers. To explain the prediction of classifiers, an intuitive way is to visualize...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 32(2023) vom: 21., Seite 4393-4406
1. Verfasser: Liu, Sixuan (VerfasserIn)
Weitere Verfasser: Li, Jingzhi, Zhang, Hua, Xu, Long, Cao, Xiaochun
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2023
Zugriff auf das übergeordnete Werk:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:Journal Article