Exploring the Robustness of Human Parsers Toward Common Corruptions

Human parsing aims to segment each pixel of the human image with fine-grained semantic categories. However, current human parsers trained with clean data are easily confused by numerous image corruptions such as blur and noise. To improve the robustness of human parsers, in this paper, we construct...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 32(2023) vom: 28., Seite 5394-5407
1. Verfasser: Zhang, Sanyi (VerfasserIn)
Weitere Verfasser: Cao, Xiaochun, Wang, Rui, Qi, Guo-Jun, Zhou, Jie
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