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...

全面介紹

書目詳細資料

Principais autores:	Feng Qian, Juan Yang, Sipeng Tang, Gao Chen, Jingwen Yan
格式:	Artigo
語言:	Inglês
出版:	MDPI AG 2024-08-01
叢編:	Mathematics
主題:	deep learning weakly supervised semantic segmentation uncertainty-weight transform module label noise learning
在線閱讀:	https://www.mdpi.com/2227-7390/12/16/2520
標簽:	添加標簽 沒有標簽, 成為第一個標記此記錄!