{"id":9855,"date":"2026-08-12T14:34:11","date_gmt":"2026-08-12T06:34:11","guid":{"rendered":"\/jase\/?post_type=tkuisotope&p=9855"},"modified":"2026-08-18T00:03:01","modified_gmt":"2026-08-17T16:03:01","slug":"jase-202611-34-043","status":"publish","type":"tkuisotope","link":"\/jase\/?tkuisotope=jase-202611-34-043","title":{"rendered":"Feature fusion based on multiple perspectives and deep adversarial networks for saliency object detection"},"content":{"rendered":"\n
\n
\n

<\/i> 2026<\/a><\/p>\n<\/div>\n\n\n\n

\n

<\/i> Volume 34<\/a><\/p>\n<\/div>\n\n\n\n

\n
\n
\n
\n

Qingwu Shi, Ziteng Wang, and Han Shi<\/i><\/a><\/p>\n\n\n\n

College of Information and Electronic Technology, Jiamusi University, Jiamusi, 154007, China<\/p>\n<\/div>\n\n\n\n

\n

Received: Septempter 29, 2025
Accepted:\u00a0July 04, 2026
Publication Date:\u00a0August 12, 2026<\/p>\n<\/div>\n<\/div>\n\n\n\n

\"\u4e0a\u50b3\u5716\u7247\"\n\n\n

Structure of the adaptive feature fusion network (AFFN)<\/p>\n<\/div>\n<\/div>\n\n\n\n

<\/i> Copyright <\/strong>The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0)<\/a>, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.<\/p>\n\n\n\n

Download Citation:  BibTeX <\/a>| http:\/\/dx.doi.org\/10.6180\/jase.202611_34.043<\/a>  <\/p>\n\n\n\n

Download PDF<\/a><\/p>\n\n\n\n

<\/div>\n\n\n\n

Saliency object detection (SOD) aims to identify the most visually prominent regions in an image that attract humanattention. Despite significant advancements in deep learning-based SOD methods, existing approaches still face challenges in effectively integrating multi-scale, multi-semantic, and multi-spatial features, leading to incomplete saliency prediction, blurred boundaries, and poor generalization to complex scenes. To address these issues, this paper proposes a novel SOD framework that combines multiple-perspective feature fusion (MPFF) and deep adversarial networks (DAN), named MPFF-DAN. First, a multi-perspective feature extraction module is designed to capture complementary information from three critical perspectives: (1) the spatial perspective (low-level features with precise spatial localization); (2) the semantic perspective (high-level features with strong category-aware representation); (3) the scale perspective (multi-scale features to adapt to objects of varying sizes). Second, an adaptive feature fusion network (AFFN) is proposed to dynamically weight and aggregate the multi-perspective features, leveraging a dual-attention mechanism (channel attention + spatial attention) to enhance the discrimination of salient regions while suppressing background noise. Third, a deep adversarial network is integrated into the framework, where a generator (based on an improved U-Net) generates high quality saliency maps, and a discriminator (a multi-scale convolutional neural network) distinguishes between the generated saliency maps and ground-truth masks. The adversarial training paradigm drives the generator to produce more realistic and boundary-preserving saliency results. Extensive experiments are conducted on
five benchmark datasets using four evaluation metrics. Quantitative and qualitative results demonstrate that MPFF-DAN outperforms 15 state-of-the-art (SOTA) methods. It maintains high efficiency with a computational complexity.<\/p>\n\n\n\n

Keywords: Saliency object detection; Feature fusion; Multiple perspectives; Adversarial networks; Attention mechanism<\/em><\/p>\n\n\n\n

<\/div>\n\n\n\n
\n
\n
\n
    \n
  1. [1] A. Borji, M.-M. Cheng, Q. Hou, H. Jiang, and J. Li, (2019) \u201cSalient object detection: A survey\u201d Computational visual media 5(2): 117\u2013150. DOI: 10.1007\/s41095-019-0149-9.<\/li>\n
  2. [2] M. Ahmadi, N. Karimi, and S. Samavi, (2021) \u201cContext-aware saliency detection for image retargeting using convolutional neural networks\u201d Multimedia Tools and Applications 80(8): 11917\u201311941. DOI: 10.1007\/s11042-020-10185-0.<\/li>\n
  3. [3] J. Han, S. He, X. Qian, and D. Wang, (2013) \u201cAn Object-Oriented Visual Saliency Detection Framework Based on Sparse Coding Representations\u201d IEEE Transactions on Circuits Systems for Video Technology 23(12): 2009\u20132021. DOI: 10.1109\/TCSVT.2013.2242594.<\/li>\n
  4. [4] N. Ding, C. Zhang, and A. Eskandarian, (2023) \u201cSalienDet: A Saliency-based Feature Enhancement Algorithm for Object Detection for Autonomous Driving\u201d IEEE Transactions on Intelligent Vehicles 9(1): 2624\u20132635. DOI: 10.1109\/TIV.2023.3287359.<\/li>\n
  5. [5] R. Han, X. Liu, and T. Chen. \u201cYolo-SG: Salience-guided detection of small objects in medical images\u201d. In: 2022 IEEE International conference on image processing (ICIP). IEEE. 2022, 4218\u20134222. DOI: 10.1109\/ICIP46576.2022.9898077.<\/li>\n
  6. [6] G. Yuan, J. Song, and J. Li, (2025) \u201cIF-USOD: Multi-modal information fusion interactive feature enhancement architecture for underwater salient object detection\u201d Information Fusion 117: 102806. DOI: 10.1016\/j.inffus.2024.102806.<\/li>\n
  7. [7] B. Wang, M. Yang, P. Cao, and Y. Liu, (2025) \u201cA novel embedded cross framework for high-resolution salient object detection: B. Wang et al.\u201d Applied Intelligence 55(4): 277. DOI: 10.1007\/s10489-024-06073-x.<\/li>\n
  8. [8] R. Achanta, S. Hemami, F. Estrada, and S. Susstrunk. \u201cFrequency-tuned salient region detection, 2009\u201d. In: IEEE Conference on CVPR, 1597\u20131604. DOI: 10.1109\/CVPR.2009.5206596.<\/li>\n
  9. [9] T. Guo and X. Xu, (2021) \u201cSalient object detection from low contrast images based on local contrast enhancing and non-local feature learning\u201d The Visual Computer 37(8): 2069\u20132081. DOI: 10.1007\/s00371-020-01964-9.<\/li>\n
  10. [10] C. Yang, L. Zhang, H. Lu, X. Ruan, and M.-H. Yang. \u201cSaliency detection via graph-based manifold ranking\u201d. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2013, 3166\u20133173. DOI: 10.1109\/CVPR.2013.407.<\/li>\n
  11. [11] M. W. Ahmed, A. Alazeb, N. Al Mudawi, T. Sadiq, B. Alabdullah, A. Algarni, A. Jalal, et al., (2025) \u201cPerception of Natural Scenes: Objects Detection and Segmentations using Saliency Map with AlexNet.\u201d International Arab Journal of Information Technology (IAJIT) 22(3): DOI: 10.34028\/iajit\/22\/3\/4.<\/li>\n
  12. [12] Y. Zhang, (2025) \u201cImage Denoising Based On Deep Feature Fusion And U-Net Network\u201d 28(10): 2277\u20132285. DOI: 10.6180\/jase.202510_28(10).0020.<\/li>\n
  13. [13] Y. Tang, X. Wu, and W. Bu. \u201cDeeply-supervised recurrent convolutional neural network for saliency detection\u201d. In: Proceedings of the 24th ACM international conference on Multimedia. 2016, 397\u2013401. DOI: 10.1145\/2964284.2967250.<\/li>\n
  14. [14] K. Alahmadi, S. Alharbi, and X. Wang, (2025) \u201cIntegrating dense layers with residual connections into transformers for enhanced sentiment classification\u201d The Journal of Supercomputing 81(16): 1\u201328. DOI: 10.1007\/s11227-025-07971-8.<\/li>\n
  15. [15] X. Qin, Z. Zhang, C. Huang, C. Gao, M. Dehghan, and M. Jagersand. \u201cBasnet: Boundary-aware salient object detection\u201d. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2019, 7479\u20137489. DOI: 10.1109\/CVPR.2019.00766.<\/li>\n
  16. [16] M. Ma, C. Xia, and J. Li. \u201cPyramidal feature shrinking for salient object detection\u201d. In: Proceedings of the AAAI conference on artificial intelligence. 35. 3. 2021, 2311\u20132318. DOI: 10.1609\/aaai.v35i3.16331.<\/li>\n
  17. [17] M.-M. Cheng, S.-H. Gao, A. Borji, Y.-Q. Tan, Z. Lin, and M. Wang, (2021) \u201cA highly efficient model to study the semantics of salient object detection\u201d IEEE Transactions on Pattern Analysis and Machine Intelligence 44(11): 8006\u20138021. DOI: 10.1109\/TPAMI.2021.3107956.<\/li>\n
  18. [18] R. Elakkiya, K. S. S. Teja, L. Jegatha Deborah, C. Bisogni, and C. Medaglia, (2022) \u201cImaging based cervical cancer diagnostics using small object detection-generative adversarial networks\u201d Multimedia Tools and Applications 81(1): 191\u2013207. DOI: 10.1007\/s11042-021-10627-3.<\/li>\n
  19. [19] H. Qiu and K. Zhang, (2025) \u201cMulti-scale adaptive graph convolution-based thick cloud removal method for optical remote sensing images\u201d International Journal of Information and Communication Technology 26(15): 57\u201377. DOI: 10.1504\/IJICT.2025.146369.<\/li>\n
  20. [20] W. Deng, L. Zheng, Q. Ye, G. Kang, Y. Yang, and J. Jiao. \u201cImage-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification\u201d. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2018, 994\u20131003. DOI: 10.1109\/CVPR.2018.00110.<\/li>\n
  21. [21] J. Wang, M. Jung, S. Yin, and H. Li, (2025) \u201cAdaptive Multi-Scale Gated Convolution and Context-Aware Attention Network for Accurate Small Object Detection [J]\u201d International Journal of Computational Methods and Experimental Measurements 13(3): 576\u2013587. DOI: 10.56578\/ijcmem130308.<\/li>\n
  22. [22] D.-P. Fan, C. Gong, Y. Cao, B. Ren, M.-M. Cheng, and A. Borji, (2018) \u201cEnhanced-alignment measure for binary foreground map evaluation\u201d arXiv preprint arXiv:1805.10421: DOI: 10.48550\/arXiv.1805.10421.<\/li>\n<\/ol>\n<\/div>\n<\/div>\n<\/div>\n\n\n\n

    <\/p>\n","protected":false},"author":3,"template":"wp-custom-template-detail-4-aricles","meta":{"_uag_custom_page_level_css":""},"categories":[12,1682,6],"tags":[1725],"acf":[],"uagb_featured_image_src":[],"uagb_author_info":{"display_name":"\u6797\u923a\u6db5","author_link":"\/jase\/?author=3"},"uagb_comment_info":0,"uagb_excerpt":" Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited. Download Citation:  BibTeX | http:\/\/dx.doi.org\/10.6180\/jase.202611_34.043   Download PDF Saliency object detection (SOD) aims to identify the most visually prominent…","_links":{"self":[{"href":"\/jase\/index.php?rest_route=\/wp\/v2\/tkuisotope\/9855"}],"collection":[{"href":"\/jase\/index.php?rest_route=\/wp\/v2\/tkuisotope"}],"about":[{"href":"\/jase\/index.php?rest_route=\/wp\/v2\/types\/tkuisotope"}],"author":[{"embeddable":true,"href":"\/jase\/index.php?rest_route=\/wp\/v2\/users\/3"}],"wp:attachment":[{"href":"\/jase\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=9855"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"\/jase\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=9855"},{"taxonomy":"post_tag","embeddable":true,"href":"\/jase\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=9855"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}