一种轻量化边界感知的极限下采样显著性目标检测网络
A Lightweight Boundary-Aware Extreme Downsampling Network for Salient Object Detection
DOI: 10.12677/csa.2026.167253, PDF,   
作者: 慈兆会*：合肥测准量子科技有限公司，安徽 合肥；聂广远：合肥工业大学计算机与信息学院，安徽 合肥
关键词: 显著性目标检测；轻量化网络；极限下采样；边界注意力；多尺度特征融合；Salient Object Detection； Lightweight Network； Extremely-Downsampled； Boundary Attention； Multi-Scale Feature Fusion
摘要: 显著性目标检测(SOD)旨在从复杂场景中定位最具视觉吸引力的区域，是图像分割和目标识别的重要预处理步骤。针对现有极限下采样网络(EDN)存在的深层下采样冗余、多尺度特征融合不足及边界表达能力弱的问题，本文提出轻量化边界感知极限下采样网络(LB-EDN)。具体包括：设计轻量极限下采样模块(Light-EDB)以保留高层语义信息并降低计算复杂度；提出分组尺度相关金字塔卷积(Group-SCPC)实现轻量多尺度特征建模；构建轻量边界注意力模块(LBA)提升边界清晰度和结构对齐；并对解码器进行通道压缩与模块轻量化设计。LB-EDN在六个公开数据集上的实验表明，其总参数量仅1.73 M，计算量2.04 G FLOPs，同时在DUTS-TE上达成Max Fβ 0.8521、MAE 0.0472、S-measure 0.9513、E-measure 0.9436，相较原EDN-Lite明显提升。结果验证了方法在结构一致性、边界表达及轻量化部署上的有效性，适用于资源受限边缘设备。
Abstract: Salient object detection (SOD) aims to locate the most visually attractive regions in complex scenes and serves as a crucial preprocessing step for image segmentation and object recognition. To address the limitations of existing extremely-downsampled networks (EDN), including redundant deep downsampling, inefficient multi-scale feature fusion, and weak boundary representation, this paper proposes a Lightweight Boundary-aware EDN (LB-EDN). Specifically, we design a Lightweight Extremely-Downsampled Block (Light-EDB) to retain high-level semantic information while reducing computational cost; introduce Group Scale-Correlated Pyramid Convolution (Group-SCPC) for efficient multi-scale feature modeling; develop a Light Boundary Attention (LBA) module to enhance boundary clarity and structural alignment; and perform channel compression and module light-weighting in the decoder. Extensive experiments on six public datasets demonstrate that LB-EDN achieves only 1.73 M parameters and 2.04 G FLOPs, while delivering strong performance. On DUTS-TE, it achieves Max Fβ 0.8521, MAE 0.0472, S-measure 0.9513, and E-measure 0.9436, showing clear improvements over the original EDN-Lite. These results validate the effectiveness of LB-EDN in structural consistency, boundary clarity, and lightweight deployment, making it suitable for resource-constrained edge devices.
文章引用：慈兆会, 聂广远. 一种轻量化边界感知的极限下采样显著性目标检测网络[J]. 计算机科学与应用, 2026, 16(7): 212-225. https://doi.org/10.12677/csa.2026.167253

参考文献

[1] Cheng, M. and Fan, D. (2021) Structure-Measure: A New Way to Evaluate Foreground Maps. International Journal of Computer Vision, 129, 2622-2638.
https://doi.org/10.1007/s11263-021-01490-8
[2] Fan, D., Gong, C., Cao, Y., Ren, B., Cheng, M. and Borji, A. (2018) Enhanced-Alignment Measure for Binary Foreground Map Evaluation. Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, Stockholm, 13-19 July 2018, 698-704.
https://doi.org/10.24963/ijcai.2018/97
[3] Achanta, R., Hemami, S., Estrada, F. and Susstrunk, S. (2009) Frequency-Tuned Salient Region Detection. 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, 20-25 June 2009, 1597-1604.
https://doi.org/10.1109/cvpr.2009.5206596
[4] Ma, Y.F., Hua, X.S., Lu, L. and Zhang, H.J. (2005) A Generic Framework of User Attention Model and Its Application in Video Summarization. IEEE Transactions on Multimedia, 7, 907-919.
https://doi.org/10.1109/tmm.2005.854410
[5] Saporta, A., Gui, X., Agrawal, A., et al. (2022) Benchmarking Saliency Methods for Chest X-Ray Interpretation. Nature Machine Intelligence, 4, 867-878.
https://doi.org/10.1038/s42256-022-00536-x
[6] Itti, L., Koch, C. and Niebur, E. (1998) A Model of Saliency-Based Visual Attention for Rapid Scene Analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20, 1254-1259.
https://doi.org/10.1109/34.730558
[7] Harel, J., Koch, C. and Perona, P. (2007) Graph-Based Visual Saliency. In: Schölkopf, B., Platt, J. and Hofmann, T., Eds., Advances in Neural Information Processing Systems 19, The MIT Press, 545-552.
https://doi.org/10.7551/mitpress/7503.003.0073
[8] Martin, D.R., Fowlkes, C.C. and Malik, J. (2004) Learning to Detect Natural Image Boundaries Using Local Brightness, Color, and Texture Cues. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26, 530-549.
https://doi.org/10.1109/tpami.2004.1273918
[9] Hou, Q., Cheng, M., Hu, X., Borji, A., Tu, Z. and Torr, P. (2017) Deeply Supervised Salient Object Detection with Short Connections. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, 21-26 July 2017, 5300-5309.
https://doi.org/10.1109/cvpr.2017.563
[10] Qin, X.B., Zhang, Z.C., Huang, C.Y., Dehghan, M., Zaiane, O.R. and Jagersand, M. (2020) U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection. Pattern Recognition, 106, Article ID: 107404.
https://doi.org/10.1016/j.patcog.2020.107404
[11] He, Y., Zhang, X. and Sun, J. (2017) Channel Pruning for Accelerating Very Deep Neural Networks. 2017 IEEE International Conference on Computer Vision (ICCV), Venice, 22-29 October 2017, 1398-1406.
https://doi.org/10.1109/iccv.2017.155
[12] Courbariaux, M., Hubara, I., Soudry, D., et al. (2016) Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or-1. arXiv: 1602.02830.
[13] Hinton, G., Vinyals, O. and Dean, J. (2015) Distilling the Knowledge in a Neural Network. arXiv: 1503.02531.
[14] Sandler, M., Howard, A., Zhu, M., Zhmoginov, A. and Chen, L. (2018) MobileNetV2: Inverted Residuals and Linear Bottlenecks. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, 18-23 June 2018, 4510-4520.
https://doi.org/10.1109/cvpr.2018.00474
[15] Zhang, X., Zhou, X., Lin, M. and Sun, J. (2018) ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, 18-23 June 2018, 6848-6856.
https://doi.org/10.1109/cvpr.2018.00716
[16] Wu, Y., Liu, Y., Zhang, L., Cheng, M. and Ren, B. (2022) EDN: Salient Object Detection via Extremely-Downsampled Network. IEEE Transactions on Image Processing, 31, 3125-3136.
https://doi.org/10.1109/tip.2022.3164550
[17] Long, J., Shelhamer, E. and Darrell, T. (2015) Fully Convolutional Networks for Semantic Segmentation. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, 7-12 June 2015, 3431-3440.
https://doi.org/10.1109/cvpr.2015.7298965
[18] Guanbin Li, and Yu, Y. (2015) Visual Saliency Based on Multiscale Deep Features. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, 7-12 June 2015, 5455-5463.
https://doi.org/10.1109/cvpr.2015.7299184
[19] Zhao, H., Shi, J., Qi, X., Wang, X. and Jia, J. (2017) Pyramid Scene Parsing Network. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, 21-26 July 2017, 6230-6239.
https://doi.org/10.1109/cvpr.2017.660
[20] Chen, L., Papandreou, G., Kokkinos, I., Murphy, K. and Yuille, A.L. (2018) DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40, 834-848.
https://doi.org/10.1109/tpami.2017.2699184
[21] Liu, J., Hou, Q., Cheng, M., Feng, J. and Jiang, J. (2019) A Simple Pooling-Based Design for Real-Time Salient Object Detection. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, 15-20 June 2019, 3912-3921.
https://doi.org/10.1109/cvpr.2019.00404
[22] Liu, N., Han, J. and Yang, M. (2018) PiCANet: Learning Pixel-Wise Contextual Attention for Saliency Detection. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, 18-23 June 2018, 3089-3098.
https://doi.org/10.1109/cvpr.2018.00326
[23] Chen, S., Tan, X., Wang, B. and Hu, X. (2018) Reverse Attention for Salient Object Detection. In: Ferrari, V., Hebert, M., Sminchisescu, C. and Weiss, Y., Eds., Computer Vision—ECCV 2018, Springer, 236-252.
https://doi.org/10.1007/978-3-030-01240-3_15
[24] Liu, N., Han, J. and Yang, M.H. (2019) BASNet: Boundary-Aware Salient Object Detection. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, 15-20 June 2019, 7479-7489.
[25] Wang, T., Borji, A., Zhang, L., Zhang, P. and Lu, H. (2017) A Stagewise Refinement Model for Detecting Salient Objects in Images. 2017 IEEE International Conference on Computer Vision (ICCV), Venice, 22-29 October 2017, 4039-4048.
https://doi.org/10.1109/iccv.2017.433
[26] Zhao, J., Liu, J., Fan, D., Cao, Y., Yang, J. and Cheng, M. (2019) EGNet: Edge Guidance Network for Salient Object Detection. 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, 27 October-2 November 2019, 8778-8787.
https://doi.org/10.1109/iccv.2019.00887
[27] Wu, Z., Su, L. and Huang, Q. (2019) Cascaded Partial Decoder for Fast and Accurate Salient Object Detection. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, 15-20 June 2019, 3902-3911.
https://doi.org/10.1109/cvpr.2019.00403
[28] Li, G. and Yu, Y. (2016) Deep Contrast Learning for Salient Object Detection. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 27-30 June 2016, 478-487.
https://doi.org/10.1109/cvpr.2016.58
[29] Yang, C., Zhang, L., Lu, H., Ruan, X. and Yang, M. (2013) Saliency Detection via Graph-Based Manifold Ranking. 2013 IEEE Conference on Computer Vision and Pattern Recognition, Portland, 23-28 June 2013, 3166-3173.
https://doi.org/10.1109/cvpr.2013.407
[30] Li, Y., Hou, X., Koch, C., Rehg, J.M. and Yuille, A.L. (2014) The Secrets of Salient Object Segmentation. 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, 23-28 June 2014, 280-287.
https://doi.org/10.1109/cvpr.2014.43
[31] Yan, Q., Xu, L., Shi, J. and Jia, J. (2013) Hierarchical Saliency Detection. 2013 IEEE Conference on Computer Vision and Pattern Recognition, Portland, 23-28 June 2013, 1155-1162.
https://doi.org/10.1109/cvpr.2013.153
[32] Movahedi, V. and Elder, J.H. (2010) Design and Perceptual Validation of Performance Measures for Salient Object Segmentation. 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition—Workshops, San Francisco, 13-18 June 2010, 49-56
https://doi.org/10.1109/cvprw.2010.5543739
[33] Li, X., Lu, H., Zhang, L., Ruan, X. and Yang, M. (2013) Saliency Detection via Dense and Sparse Reconstruction. 2013 IEEE International Conference on Computer Vision, Sydney, 1-8 December 2013, 2976-2983.
https://doi.org/10.1109/iccv.2013.370