.png){kind=icon}
.png){kind=icon}
Return
Complementary characteristics fusion network for weakly supervised salient object detection
.png){kind=icon}
OA
AI
DOI：10.1016/j.imavis.2022.104536.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Salient object detection (SOD) is a challenging and fundamental research in computer vision and image process-ing. Since the cost of pixel-level annotations is high, scribble annotations are usually used as weak supervisions. However, scribble annotations are too sparse and always located inside the objects with lacking annotations close to the semantic boundaries, which can't make confident predictions. To alleviate these issues, we propose a novel and effective scribble-based weakly supervised approach for SOD, named complementary characteristics fusion network (CCFNet). To be more specific, we design an edge fusion module (EFM) by taking account of local and high-level semantic information to equip our model, which would be beneficial to enhance the power of aggre-gating edge information. Then to achieve the complementary role of different features, a series of feature corre-lation modules (FCMs) are employed to strengthen the localization information and details learning. This is based on low-level, high-level global and edge information, which will complement each other to obtain relatively complete salient regions. Alternatively, to encourage the network to learn structural information and further im-prove the results of saliency maps in foreground and background, we propose a self-supervised salient detection (SSD) loss. Extensive experiments using five benchmark datasets demonstrate that our proposed approach per-forms favorably against the state-of-the-art weakly supervised algorithms, and even surpasses the performance of those fully supervised.(c) 2022 Published by Elsevier B.V.
Keywords:
Salient object detection
Weakly supervised learning
Edge fusion module
Feature correlation module
Self-supervised salient detection loss
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
4.2
Papers:
4.0K
Citations:
6.7K