Addressing Noisy Pixels in Weakly Supervised Semantic Segmentation with Weights Assigned

Weakly supervised semantic segmentation (WSSS) aims to segment objects without a heavy burden of dense annotations. Pseudo-masks serve as supervisory information for training segmentation models, which is crucial to the performance of segmentation models. However, the generated pseudo-masks contain...

תיאור מלא

מידע ביבליוגרפי

Principais autores:	Feng Qian, Juan Yang, Sipeng Tang, Gao Chen, Jingwen Yan
פורמט:	Artigo
שפה:	Inglês
יצא לאור:	MDPI AG 2024-08-01
סדרה:	Mathematics
נושאים:	deep learning weakly supervised semantic segmentation uncertainty-weight transform module label noise learning
גישה מקוונת:	https://www.mdpi.com/2227-7390/12/16/2520
תגים:	הוספת תג אין תגיות, היה/י הראשונ/ה לתייג את הרשומה!