Addressing Noisy Pixels in Weakly Supervised Semantic Segmentation with Weights Assigned

Feng Qian, Juan Yang, Sipeng Tang, Gao Chen () and Jingwen Yan
Additional contact information
Feng Qian: Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, China
Juan Yang: College of Engineering, Shantou University, Shantou 515063, China
Sipeng Tang: China Mobile Communications Group Guangdong Co., Ltd. Shantou Branch, Shantou 515041, China
Gao Chen: School of Telecommunications Engineering and Intelligentization, Dongguan University of Technology, Dongguan 523808, China
Jingwen Yan: College of Engineering, Shantou University, Shantou 515063, China

Mathematics, 2024, vol. 12, issue 16, 1-17

Abstract: 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 significant noisy labels, which leads to poor performance of the segmentation models trained on these pseudo-masks. Few studies address this issue, as these noisy labels remain inevitable even after the pseudo-masks are improved. In this paper, we propose an uncertainty-weight transform module to mitigate the impact of noisy labels on model performance. It is noteworthy that our approach is not aimed at eliminating noisy labels but rather enhancing the robustness of the model to noisy labels. The proposed method adopts a frequency-based approach to estimate pixel uncertainty. Moreover, the uncertainty of pixels is transformed into loss weights through a set of well-designed functions. After dynamically assigning weights, the model allocates attention to each pixel in a significantly differentiated manner. Meanwhile, the impact of noisy labels on model performance is weakened. Experiments validate the effectiveness of the proposed method, achieving state-of-the-art results of 69.3% on PASCAL VOC 2012 and 39.3% on MS COCO 2014, respectively.

Keywords: deep learning; weakly supervised semantic segmentation; uncertainty-weight transform module; label noise learning (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/12/16/2520/pdf (application/pdf)
https://www.mdpi.com/2227-7390/12/16/2520/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:12:y:2024:i:16:p:2520-:d:1456899

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().