Position Fusing and Refining for Clear Salient Object Detection

Xing Zhao

doi:10.1109/TNNLS.2022.3213557

Position Fusing and Refining for Clear Salient Object Detection

2025-03-01

5

PRE

AI

DOI：10.1109/TNNLS.2022.3213557

原文链接

原文求助

摘要

En 中文

Multilevel feature fusion plays a pivotal role in salient object detection (SOD). High-level features present rich semantic information but lack object position information, whereas low-level features contain object position information but are mixed with noises such as backgrounds. Appropriately addressing the gap between low-and high-level features is important in SOD. We first propose a global position embedding attention (GPEA) module to minimize the discrepancy between multilevel features in this article. We extract the position information by utilizing the semantic information at high-level features to resist noises at low-level features. Object refine attention (ORA) module is introduced to refine features used to predict saliency maps further without any additional supervision and heighten discriminative regions near the salient object, such as boundaries. Moreover, we find that the saliency maps generated by the previous methods contain some blurry regions, and we design a pixel value (PV) loss to help the model generate saliency maps with improved clarity. Experimental results on five commonly used SOD datasets demonstrated that the proposed method is effective and outperforms the state-of-the-art approaches on multiple metrics.

Keyword:

Feature extraction

Semantics

Decoding

Resists

Image edge detection

Task analysis

Learning systems

Attention

clear saliency map

deep learning

feature fusion

salient object detection (SOD)

Position Fusing and Refining for Clear Salient Object Detection

摘要

期刊

机构

引用论文