Local saliency consistency‐based label inference for weakly supervised salient object detection using scribble annotations
Abstract Recently, weak supervision has received growing attention in the field of salient object detection due to the convenience of labelling. However, there is a large performance gap between weakly supervised and fully supervised salient object detectors because the scribble annotation can only...
Main Authors: | Shuo Zhao, Peng Cui, Jing Shen, Haibo Liu |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2024-02-01
|
Series: | CAAI Transactions on Intelligence Technology |
Subjects: | |
Online Access: | https://doi.org/10.1049/cit2.12210 |
Similar Items
-
Weakly supervised salient object detection via image category annotation
by: Ruoqi Zhang, et al.
Published: (2023-12-01) -
Hyperspectral Images Weakly Supervised Classification with Noisy Labels
by: Chengyang Liu, et al.
Published: (2023-10-01) -
Learning Consistency From High-Confidence Pseudo-Labels for Weakly Supervised Object Localization
by: Kangbo Sun, et al.
Published: (2023-01-01) -
A simple information fusion method provides the obstacle with saliency labeling as a landmark in robotic mapping
by: Lihe Hu, et al.
Published: (2022-12-01) -
Visibility Estimation Based on Weakly Supervised Learning under Discrete Label Distribution
by: Qing Yan, et al.
Published: (2023-11-01)