Semantic Guided Feature Aggregation Network for Salient Object Detection

被引：0

作者：

Wang Z.-W. ^{[1
]}

Song H.-H. ^{[1
]}

Fan J.-Q. ^{[1
]}

Liu Q.-S. ^{[1
]}

机构：

[1] Jiangsu Key Laboratory of Big Data Analysis Technology, Collaborative InnovationCenter on Atmospheric Environment and Equipment Technology, Nanjing University of Information Science and Technology, Nanjing

来源：

Zidonghua Xuebao/Acta Automatica Sinica | 2023年 / 49卷 / 11期

基金：

中国国家自然科学基金;

关键词：

deep learning; mixing attention; multi-level aggregation; Salient object detection;

D O I：

10.16383/j.aas.c210425

中图分类号：

学科分类号：

摘要：

In the field of the salient object detection, the U-shaped structure has attracted much attention. However, the spatial and boundary details are ignored in the U-shaped salient object detection task. To address the issues, this paper proposes a salient object detection network that uses semantic information to guide feature aggregation, mainly including three modules: Mixing attention module (MAM), enlarged receptive field module (ERFM) and multi-level aggregation module (MLAM). Specifically, utilizes ERFM to process the low-level features, so that it can increase the receptive field while retaining the original edge details to obtain richer spatial context information. Then, utilize the MAM to process the high-level features to enhance its semantic representation, which guides the feature aggregation in the decoding process. Finally, MLAM is employed to effectively combine the multilevel features for the predicted salient map. This paper conducts extensive experiments on 6 benchmarks, and the results have proved that the method can effectively locate salient object and refine edge details. © 2023 Science Press. All rights reserved.

引用

页码：2386 / 2395

页数：9

共 41 条

[1]

Donoser M, Urschler M, Hirzer M, Bischof H., Saliency driven total variation segmentation, Proceedings of the IEEE International Conference on Computer Vision, pp. 817-824, (2009)

[2]

Wei J, Wang S, Huang Q., F3Net: Fusion, feedback and focus for salient object detection, Proceedings of the AAAI Conference on Artificial Intelligence, pp. 12321-12328, (2020)

[3]

Li Dong-Min, Li Jing, Liang Da-Chuan, Wang Chao, Multiple salient objects detection using multi-scale prior and deep features, Acta Automatica Sinica, 45, 11, pp. 2058-2070, (2019)

[4]

Xu Wei, Tang Zhen-Min, Exploiting hierarchical prior estimation for salient object detection, Acta Automatica Sinica, 41, 4, pp. 799-812, (2015)

[5]

Yang Sai, Zhao Chun-Xia, Xu Wei, A novel salient object detection method using bag-of-features, Acta Automatica Sinica, 42, 8, pp. 1259-1273, (2016)

[6]

Hong S, You T, Kwak S, Han B., Online tracking by learning discriminative saliency map with convolutional neural network, Proceedings of the 32nd International Conference on Machine Learning, pp. 597-606, (2015)

[7]

Ren Z, Gao S, Chia L, Tsang I W., Region-based saliency detection and its application in object recognition, IEEE Transactions on Circuits and Systems for Video Technology, 24, 5, pp. 769-779, (2014)

[8]

Wang X, You S, Li X, Ma H., Weakly-supervised semantic segmentation by iteratively mining common object features, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1354-1362, (2018)

[9]

Goferman S, Zelnik-Manor L, Tal A., Context-aware saliency detection, IEEE Transactions on Pattern Analysis and Machine Intelligence, 34, 10, pp. 1915-1926, (2012)

[10]

Yan Q, Xu L, Shi J, Jia J., Hierarchical saliency detection, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1155-1162, (2013)

← 1 2 3 4 5 →