基于无源领域自适应的低光照显著性目标检测

doi:10.19678/j.issn.1000-3428.0069704

摘要/Abstract

摘要：

为了解决低光照条件下校园环境等场景监控摄像头图像质量和监控效果受影响而带来的安全问题, 提出一种低光照显著性目标检测(SOD)方法, 以提高低光照条件下目标检测能力。针对低光照条件下图像的显著性特征弱化和缺乏大规模标注数据的问题, 提出一种无源领域自适应(SFDA)方法, 将正常光照图像(源域)下训练的模型知识迁移至低光照条件图像(目标域)。该方法采用两阶段策略: 在第一阶段, 利用源域模型生成低光照图像的伪标签, 为提高伪标签生成的质量, 提出集合熵最小化损失抑制高熵区域, 同时引入选择性投票方法来增强伪标签的生成; 在第二阶段, 采用基于增强引导一致性的教师-学生网络自训练方法对显著图进行精细化, 进一步提高检测结果的精度。在SOD-LL数据集上的实验结果表明, 所提出的方法在低光照场景下总体性能优于其他图像显著性检测方法, 相较于正常光照的SOD方法, 其平均绝对误差(MAE)降低15.15%, 加权F1值(wF_m)提高4.73%。

关键词: 显著性目标检测, 低光照场景, 无源领域自适应, 伪标签, 教师-学生网络, 集合熵最小化, 选择性投票

Abstract:

To address the security issues arising from the degradation of image quality and monitor the effectiveness of surveillance cameras in low-light campus environments, a low-light Salient Object Detection (SOD) method is proposed to enhance target detection capability under low-light conditions. Given the challenges of weakened salient features and the lack of large-scale annotated data in low-light images, a Source-Free Domain Adaptation (SFDA) method for low-light SOD is proposed to transfer the model knowledge trained on normal-lighting images (source domain) to low-light images (target domain). The proposed method employs a two-stage strategy. In the first stage, pseudo-labels for low-light images are generated using the source domain model. To improve the quality of the pseudo-label generation, an ensemble entropy minimization loss is proposed to suppress high-entropy regions. In addition, a selective voting method is introduced to enhance pseudo-label generation. In the second stage, a teacher-student network self-training method based on enhanced guided consistency is employed to refine the saliency maps, further improving the accuracy of the detection results. Experimental results on the SOD-LL dataset show that the proposed method outperforms other image saliency detection methods in low-light scenarios. Compared to normal-light SOD methods, the Mean Absolute Error (MAE) is reduced by 15.15%, and the Weighted F1 value(wF_m) is increased by 4.73%.

Key words: Salient Object Detection (SOD), low-light scenes, Source-Free Domain Adaption (SFDA), pseudo-label, teacher-student network, ensemble entropy minimization, selective voting

李书玮, 黄正翔, 胡云, 刘兴, 卢笑, 郭畅, 吴成中, 王耀南. 基于无源领域自适应的低光照显著性目标检测[J]. 计算机工程, 2025, 51(4): 75-84.

LI Shuwei, HUANG Zhengxiang, HU Yun, LIU Xing, LU Xiao, GUO Chang, WU Chengzhong, WANG Yaonan. Low-Light Salient Object Detection Based on Source-Free Domain Adaptation[J]. Computer Engineering, 2025, 51(4): 75-84.

https://www.ecice06.com/CN/Y2025/V51/I4/75

图/表 10

图1 本文方法整体框架

Fig.1 Overall framework of the proposed method

图2 数据增强可视化结果

Fig.2 Data augmentation visualization results

图3 选择性投票策略示意图

Fig.3 Schematic diagram of the selective voting strategy

图4 本文方法和其他SOD方法得到的可视化结果

Fig.4 Visualization results obtained by the proposed method and other SOD methods

图5 选择性投票方法的消融实验可视化结果

Fig.5 Visualization results of ablation experiments on the selective voting method

参考文献 36

1	WANG W G, LAI Q X, FU H Z, et al. Salient object detection in the deep learning era: an in-depth survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44(6): 3239- 3259. doi: 10.1109/TPAMI.2021.3051099
2	WANG L J, LU H C, WANG Y F, et al. Learning to detect salient objects with image-level supervision[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Washington D. C., USA: IEEE Press, 2017: 136-145.
3	LU X, YUAN Y L, LIU X, et al. Low-light salient object detection by learning to highlight the foreground objects. IEEE Transactions on Circuits and Systems for Video Technology, 2024, 34(8): 7712- 7724. doi: 10.1109/TCSVT.2024.3377108
4	MA M C, XIA C Q, LI J. Pyramidal feature shrinking for salient object detection. Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 35(3): 2311- 2318. doi: 10.1609/aaai.v35i3.16331
5	YANG S, LIN W S, LIN G S, et al. Progressive self-guided loss for salient object detection. IEEE Transactions on Image Processing, 2021, 30, 8426- 8438. doi: 10.1109/TIP.2021.3113794
6	VU T H, JAIN H, BUCHER M, et al. ADVENT: adversarial entropy minimization for domain adaptation in semantic segmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D. C., USA: IEEE Press, 2019: 2517-2526.
7	张晴, 左保川, 石艳娇, 等. 多尺度卷积神经网络显著物体检测. 中国图象图形学报, 2020, 25(6): 1116- 1129.
	ZHANG Q, ZUO B C, SHI Y J, et al. Multi-scale convolutional neural network for salient object detection. Journal of Image and Graphics, 2020, 25(6): 1116- 1129.
8	刘迪, 郭继昌, 汪昱东, 等. 融合注意力机制的多尺度显著性目标检测网络. 西安电子科技大学学报, 2022, 49(4): 118- 126.
	LIU D, GUO J C, WANG Y D, et al. Multi-scale salient object detection network combining attention mechanism. Journal of Xidian University, 2022, 49(4): 118- 126.
9	WU Y H, LIU Y, ZHANG L, et al. EDN: salient object detection via extremely-downsampled network. IEEE Transactions on Image Processing, 2022, 31, 3125- 3136. doi: 10.1109/TIP.2022.3164550
10	MA M C, XIA C Q, XIE C X, et al. Boosting broader receptive fields for salient object detection. IEEE Transactions on Image Processing, 2023, 32, 1026- 1038. doi: 10.1109/TIP.2022.3232209
11	GAO S Y, ZHANG W, WANG Y, et al. Weakly-supervised salient object detection using point supervision. Proceedings of the AAAI Conference on Artificial Intelligence, 2022, 36(1): 670- 678. doi: 10.1609/aaai.v36i1.19947
12	LIU J, ZHANG J, BARNES N. Semi-supervised salient object detection with effective confidence estimation[EB/OL]. [2024-03-02]. https://arxiv.org/abs/2112.14019.
13	LIN X R, WU Z Y, CHEN G Q, et al. A causal debiasing framework for unsupervised salient object detection. Proceedings of the AAAI Conference on Artificial Intelligence, 2022, 36(2): 1610- 1619. doi: 10.1609/aaai.v36i2.20052
14	穆楠. 夜间场景下显著目标检测方法研究[D]. 武汉: 武汉科技大学, 2019.
	MU N. Research on detection method of salient targets in night scene[D]. Wuhan: Wuhan University of Science and Technology, 2019. (in Chinese)
15	LI R, JIAO Q F, CAO W M, et al. Model adaptation: unsupervised domain adaptation without source data[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D. C., USA: IEEE Press, 2020: 9641-9650.
16	YOU F M, LI J J, ZHU L, et al. Domain adaptive semantic segmentation without source data[C]//Proceedings of the 29th ACM International Conference on Multimedia. New York, USA: ACM Press, 2021: 3293-3302.
17	CHEN Y X, LIN M W, HE Z, et al. Consistency-and dependence-guided knowledge distillation for object detection in remote sensing images. Expert Systems with Applications, 2023, 229, 120519. doi: 10.1016/j.eswa.2023.120519
18	TANG Y H, CHEN W F, LUO Y J, et al. Humble teachers teach better students for semi-supervised object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D. C., USA: IEEE Press, 2021: 3132-3141.
19	XIE Q Z, LUONG M T, HOVY E, et al. Self-training with noisy student improves ImageNet classification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D. C., USA: IEEE Press, 2020: 10687-10698.
20	LI C, CHEN W, LUO X, et al. Adaptive pseudo labeling for source-free domain adaptation in medical image segmentation[C]//Proceedings of the 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Washington D. C., USA: IEEE Press, 2022: 1091-1095.
21	QI Y L, YANG Z, SUN W H, et al. A comprehensive overview of image enhancement techniques. Archives of Computational Methods in Engineering, 2022, 29(1): 583- 607. doi: 10.1007/s11831-021-09587-6
22	KAPOOR K, ARORA S. Colour image enhancement based on histogram equalization. Electrical&Computer Engineering, 2015, 4(3): 73- 82.
23	LEE J, PANT S R, LEE H S. An adaptive histogram equalization based local technique for contrast preserving image enhancement. The International Journal of Fuzzy Logic and Intelligent Systems, 2015, 15(1): 35- 44. doi: 10.5391/IJFIS.2015.15.1.35
24	VIBASHAN V, VALANARASU J M J, PATEL V M. Target and task specific source-free domain adaptive image segmentation[EB/OL]. [2024-03-02]. https://arxiv.org/abs/2203.15792.
25	MILLETARI F, NAVAB N, AHMADI S A. V-Net: fully convolutional neural networks for volumetric medical image segmentation[C]//Proceedings of the 4th International Conference on 3D Vision (3DV). Washington D. C., USA: IEEE Press, 2016: 565-571.
26	WU Z, SU L, HUANG Q M. Stacked cross refinement network for edge-aware salient object detection[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). Washington D. C., USA: IEEE Press, 2019: 7264-7273.
27	WU Z, SU L, HUANG Q M. Cascaded partial decoder for fast and accurate salient object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D. C., USA: IEEE Press, 2019: 3907-3916.
28	CHEN Z Y, XU Q Q, CONG R M, et al. Global context-aware progressive aggregation network for salient object detection. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(7): 10599- 10606. doi: 10.1609/aaai.v34i07.6633
29	WEI J, WANG S H, HUANG Q M. F³Net: fusion, feedback and focus for salient object detection. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(7): 12321- 12328. doi: 10.1609/aaai.v34i07.6916
30	WEI J, WANG S H, WU Z, et al. Label decoupling framework for salient object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D. C., USA: IEEE Press, 2020: 13025-13034.
31	ZHAO Z R, XIA C Q, XIE C X, et al. Complementary trilateral decoder for fast and accurate salient object detection[C]//Proceedings of the 29th ACM International Conference on Multimedia. New York, USA: ACM Press, 2021: 4967-4975.
32	ZHU H W, LI P, XIE H R, et al. I can find you!Boundary-guided separated attention network for camouflaged object detection. Proceedings of the AAAI Conference on Artificial Intelligence, 2022, 36(3): 3608- 3616. doi: 10.1609/aaai.v36i3.20273
33	YU S Y, ZHANG B F, XIAO J M, et al. Structure-consistent weakly supervised salient object detection with local saliency coherence. Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 35(4): 3234- 3242. doi: 10.1609/aaai.v35i4.16434
34	PIAO Y R, WU W, ZHANG M, et al. Noise-sensitive adversarial learning for weakly supervised salient object detection. IEEE Transactions on Multimedia, 2023, 25, 2888- 2897. doi: 10.1109/TMM.2022.3152567
35	WANG Y F, ZHANG W B, WANG L J, et al. Multi-source uncertainty mining for deep unsupervised saliency detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D. C., USA: IEEE Press, 2022: 11727-11736.
36	CHEN C, LIU Q D, JIN Y M, et al. Source-free domain adaptive fundus image segmentation with denoised pseudo-labeling[C]//Proceedings of the 24th International Conference on Medical Image Computing and Computer Assisted Intervention. Berlin, Germany: Springer International Publishing, 2021: 225-235.

[1]	胡升龙, 陈彬, 张开华, 宋慧慧. 场景结构知识增强的协同显著性目标检测[J]. 计算机工程, 2025, 51(1): 31-41.
[2]	李沼洁, 朱恒亮, 毛国君, 杨鑫. 渐进式特征增强的弱监督显著性目标检测[J]. 计算机工程, 2024, 50(12): 233-244.
[3]	邵良杉, 赵松泽. 基于多模型融合的不完整数据分数插补算法[J]. 计算机工程, 2023, 49(9): 79-88, 98.
[4]	李军侠, 王星驰, 殷梓, 石德硕. 边缘深度挖掘的弱监督显著性目标检测[J]. 计算机工程, 2023, 49(7): 169-178.
[5]	何悦, 陈广胜, 景维鹏, 徐泽堃. 基于深度多相似性哈希方法的遥感图像检索[J]. 计算机工程, 2023, 49(2): 206-212.
[6]	刘仲任, 彭力. 多尺度视觉感知融合的显著性目标检测[J]. 计算机工程, 2023, 49(12): 186-193.
[7]	富坤, 孙明磊, 郝玉涵, 刘赢华. 基于对抗训练的伪标签约束自编码器[J]. 计算机工程, 2023, 49(11): 123-130.
[8]	雷洁, 饶文碧, 杨焱超, 熊盛武. 基于分类不确定性的伪标签目标检测算法[J]. 计算机工程, 2023, 49(1): 49-56.
[9]	王安志, 任春洪, 何淋艳, 杨元英, 欧卫华. 基于多模态多级特征聚合网络的光场显著性目标检测[J]. 计算机工程, 2022, 48(7): 227-233,240.
[10]	花卉. 多视觉特征结合有约束简化群优化的显著性目标检测[J]. 计算机工程, 2015, 41(11): 257-262.

选择文件类型/文献管理软件名称

选择包含的内容