Pansharpening based on two-stage collaborative optimization

doi:10.11772/j.issn.1001-9081.2025050598

Journal of Computer Applications ›› 2026, Vol. 46 ›› Issue (5): 1568-1577.DOI: 10.11772/j.issn.1001-9081.2025050598

• Multimedia computing and computer simulation • Previous Articles

Pansharpening based on two-stage collaborative optimization

Jiaxin DUAN, Jing HU, Wu WEN, Zhenxia YU(), Yongjun ZHANG

College of Computer Science，Chengdu University of Information Technology，Chengdu Sichuan 610225，China

Received:2025-06-04 Revised:2025-07-25 Accepted:2025-08-27 Online:2025-11-07 Published:2026-05-10
Contact: Zhenxia YU
About author:DUAN Jiaxin， born in 2000， M. S. candidate. His research interests include remote sensing image fusion.
HU Jing， born in 1986， Ph. D.， professor. Her research interests include image processing.
WEN Wu， born in 1979， Ph. D.， associate professor. His research interests include artificial intelligence， high-performance computing.
ZHANG Yongjun， born in 2004. His research interests include graphics and image processing.
Supported by:
National Natural Science Foundation of China(42375148)

基于两阶段协同优化的全色锐化

段佳欣, 胡靖, 文武, 余贞侠(), 张永俊

成都信息工程大学计算机学院，成都 610225

通讯作者: 余贞侠
作者简介:段佳欣（2000—），男，四川南充人，硕士研究生，CCF会员，主要研究方向：遥感图像融合
胡靖（1986—），女，四川成都人，教授，博士，主要研究方向：图像处理
文武（1979—），男，四川蓬溪人，副教授，博士，主要研究方向：人工智能、高性能计算
张永俊（2004—），男，广西南宁人，主要研究方向：图形图像处理。
基金资助:
国家自然科学基金资助项目(42375148)

Abstract

Abstract:

Although deep learning-based pansharpening methods for remote sensing images have made certain progress， most of them rely on supervised training with downsampled data， making them susceptible to scale bias and difficult to maintain stable performance at full resolution. In contrast， unsupervised methods optimize directly on full-resolution images， avoiding issues caused by downsampling， but generally exhibit weak robustness due to the lack of explicit supervisory signals. Therefore， a pansharpening Network based on Two-stage Collaborative Optimization （TCONet） was proposed. In the first stage， through supervised training on downsampled data， and combining an Improved Multi-Resolution Analysis （IMRA） method with an attention mechanism， spatial details and spectral preservation capability were improved. In the second stage， an Unsupervised Information Compensation Network （UCIN） was constructed to directly optimize on full-resolution images， thereby compensating for information loss caused by scale inconsistency. Experimental results on three satellite datasets： QuickBird（QB）， WorldView-2 （WV-2）， and WorldView-4 （WV-4） indicate that TCONet outperforms comparative methods in terms of both visual quality and evaluation metrics.

Key words: pansharpening, supervised learning, unsupervised learning, image fusion, remote sensing image processing

摘要：

尽管基于深度学习的遥感图像全色锐化方法取得了一定进展，但它们多数依赖降采样数据进行监督训练，易受到尺度偏差影响，难以在全分辨率条件下保持性能稳定；相比之下，无监督方法可直接在全分辨率图像上优化，规避了降采样引发的问题，但由于缺乏明确的监督信号，方法的鲁棒性普遍较弱。因此，提出一种两阶段协同优化的全色锐化网络（TCONet）。第一阶段通过在降采样数据上进行监督训练，结合改进的多分辨率分析（IMRA）方法与注意力机制，提升空间细节与光谱保持能力；第二阶段构建无监督信息补偿网络（UICN），直接在全分辨率图像上优化，弥补尺度不一致带来的信息缺失。在4波段数据集QuickBird（QB）、8波段数据集WorldView-2 （WV-2）和4波段数据集WorldView-4 （WV-4）共3个卫星数据集上的实验结果表明，TCONet的视觉效果与评价指标均优于对比方法。

关键词: 全色锐化, 监督学习, 无监督学习, 图像融合, 遥感图像处理

CLC Number:

TP751

Jiaxin DUAN, Jing HU, Wu WEN, Zhenxia YU, Yongjun ZHANG. Pansharpening based on two-stage collaborative optimization[J]. Journal of Computer Applications, 2026, 46(5): 1568-1577.

段佳欣, 胡靖, 文武, 余贞侠, 张永俊. 基于两阶段协同优化的全色锐化[J]. 《计算机应用》唯一官方网站, 2026, 46(5): 1568-1577.

Figures/Tables 15

References 42

[1]	吴宗骏，吴炜，杨晓敏，等. 改进的基于稀疏表示的全色锐化算法［J］. 计算机应用， 2019， 39（2）： 540-545.
	WU Z J， WU W， YANG X M， et al. Improved panchromatic sharpening algorithm based on sparse representation［J］. Journal of Computer Applications， 2019， 39（2）： 540-545.
[2]	ZHANG K， ZHANG F， WAN W， et al. Panchromatic and multispectral image fusion for remote sensing and earth observation： concepts， taxonomy， literature review， evaluation methodologies and challenges ahead［J］. Information Fusion， 2023， 93： 227-242.
[3]	路琨婷，费蓉蓉，张选德. 融合卷积神经网络的遥感图像全色锐化［J］.计算机应用， 2023， 43（9）： 2963-2969.
	LU K T， FEI R R， ZHANG X D. Remote sensing image pansharpening by convolutional neural network［J］. Journal of Computer Applications， 2023， 43（9）： 2963-2969.
[4]	CHOI J， YU K， KIM Y. A new adaptive component-substitution-based satellite image fusion by using partial replacement［J］. IEEE Transactions on Geoscience and Remote Sensing， 2010， 49（1）： 295-309.
[5]	OTAZU X， GONZÁLEZ-AUDÍCANA M， FORS O， et al. Introduction of sensor spectral response into image fusion methods. Application to wavelet-based methods［J］. IEEE Transactions on Geoscience and Remote Sensing， 2005， 43（10）： 2376-2385.
[6]	BURT P J， ADELSON E H. The Laplacian pyramid as a compact image code［M］// FISCHLER M A， FIRSCHEIN O. Readings in computer vision： issues， problem， principles， and paradigms. San Francisco： Morgan Kaufmann Publishers Inc.， 1987： 671-679.
[7]	AIAZZI B， ALPARONE L， BARONTI S， et al. MTF-tailored multiscale fusion of high-resolution MS and Pan imagery［J］. Photogrammetric Engineering and Remote Sensing， 2015， 72（5）： 591-596.
[8]	VIVONE G， RESTAINO R， CHANUSSOT J. Full scale regression-based injection coefficients for panchromatic sharpening［J］. IEEE Transactions on Image Processing， 2018， 27（7）： 3418-3431.
[9]	VIVONE G， DALLA MURA M， GARZELLI A， et al. A new benchmark based on recent advances in multispectral pansharpening： revisiting pansharpening with classical and emerging pansharpening methods［J］. IEEE Geoscience and Remote Sensing Magazine， 2021， 9（1）： 53-81.
[10]	FASBENDER D， RADOUX J， BOGAERT P. Bayesian data fusion for adaptable image pansharpening［J］. IEEE Transactions on Geoscience and Remote Sensing， 2008， 46（6）： 1847-1857.
[11]	ZHANG L， SHEN H， GONG W， et al. Adjustable model-based fusion method for multispectral and panchromatic images［J］. IEEE Transactions on Systems， Man， and Cybernetics， Part B （Cybernetics）， 2012， 42（6）： 1693-1704.
[12]	PALSSON F， SVEINSSON J R， ULFARSSON M O. A new pansharpening algorithm based on total variation［J］. IEEE Geoscience and Remote Sensing Letters， 2014， 11（1）： 318-322.
[13]	CAO Q， DENG L J， WANG W， et al. Zero-shot semi-supervised learning for pansharpening［J］. Information Fusion， 2024， 101： No.102001.
[14]	DIAO W， ZHANG F， SUN J， et al. ZeRGAN： zero-reference GAN for fusion of multispectral and panchromatic images［J］. IEEE Transactions on Neural Networks and Learning Systems， 2023， 34（11）： 8195-8209.
[15]	ZHOU H， LIU Q， WENG D， et al. Unsupervised cycle-consistent generative adversarial networks for pan sharpening［J］. IEEE Transactions on Geoscience and Remote Sensing， 2022， 60： No.5408814.
[16]	HE X， CONDAT L， BIOUCAS-DIAS J M， et al. A new pansharpening method based on spatial and spectral sparsity priors［J］. IEEE Transactions on Image Processing， 2014， 23（9）： 4160-4174.
[17]	SERIFOGLU YILMAZ C， YILMAZ V， GUNGOR O， et al. Metaheuristic pansharpening based on symbiotic organisms search optimization［J］. ISPRS Journal of Photogrammetry and Remote Sensing， 2019， 158： 167-187.
[18]	ZHENG S， SHI W Z， LIU J， et al. Remote sensing image fusion using multiscale mapped LS-SVM［J］. IEEE Transactions on Geoscience and Remote Sensing， 2008， 46（5）： 1313-1322.
[19]	XING Y， WANG M， YANG S， et al. Pansharpening with multiscale geometric support tensor machine［J］. IEEE Transactions on Geoscience and Remote Sensing， 2018， 56（5）： 2503-2517.
[20]	RESTAINO R， VIVONE G， DALLA MURA M， et al. Fusion of multispectral and panchromatic images based on morphological operators［J］. IEEE Transactions on Image Processing， 2016， 25（6）： 2882-2895.
[21]	ZHANG T J， DENG L J， HUANG T Z， et al. A triple-double convolutional neural network for panchromatic sharpening［J］. IEEE Transactions on Neural Networks and Learning Systems， 2023， 34（11）： 9088-9101.
[22]	BRAUWERS G， FRASINCAR F. A general survey on attention mechanisms in deep learning［J］. IEEE Transactions on Knowledge and Data Engineering， 2023， 35（4）： 3279-3298.
[23]	JADERBERG M， SIMONYAN K， ZISSERMAN A， et al. Spatial Transformer networks［C］// Proceedings of the 29th International Conference on Neural Information Processing Systems — Volume 2. Cambridge： MIT Press， 2015： 2017-2025.
[24]	HU J， SHEN L， SUN G. Squeeze-and-excitation networks［C］// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2018： 7132-7141.
[25]	WOO S， PARK J， LEE J Y， et al. CBAM： convolutional block attention module［C］// Proceedings of the 2018 European Conference on Computer Vision， LNCS 11211. Cham： Springer， 2018： 3-19.
[26]	HAN K， WANG Y， CHEN H， et al. A survey on Vision Transformer［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2023， 45（1）： 87-110.
[27]	WALD L， RANCHIN T， MANGOLINI M. Fusion of satellite images of different spatial resolutions： assessing the quality of resulting images［J］. Photogrammetric Engineering and Remote Sensing， 1997， 63（6）： 691-699.
[28]	MASI G， COZZOLINO D， VERDOLIVA L， et al. Pansharpening by convolutional neural networks［J］. Remote Sensing， 2016， 8（7）： No.594.
[29]	YANG G， ZHOU M， YAN K， et al. Memory-augmented deep conditional unfolding network for pan-sharpening［C］// Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2022： 1778-1787.
[30]	YANG J， FU X， HU Y， et al. PanNet： a deep network architecture for pan-sharpening［C］// Proceedings of the 2017 IEEE International Conference on Computer Vision. Piscataway： IEEE， 2017： 1753-1761.
[31]	JIA Y， HU Q， DIAN R， et al. PAPS： progressive attention-based pan-sharpening［J］. IEEE/CAA Journal of Automatica Sinica， 2024， 11（2）： 391-404.
[32]	YUAN Q， WEI Y， MENG X， et al. A multiscale and multidepth convolutional neural network for remote sensing imagery pan-sharpening［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing， 2018， 11（3）： 978-989.
[33]	QU Y， LI B， HUANG J， et al. Training pansharpening networks at full resolution using degenerate invariance［C］// Proceedings of the 32nd ACM International Conference on Multimedia. New York： ACM， 2024： 176-185.
[34]	MA J， YU W， CHEN C， et al. Pan-GAN： an unsupervised pan-sharpening method for remote sensing image fusion［J］. Information Fusion， 2020， 62： 110-120.
[35]	JIN X， FENG Y， JIANG Q， et al. UPGAN： an unsupervised generative adversarial network based on U-shaped structure for pansharpening［J］. ISPRS International Journal of Geo-Information， 2024， 13（7）： No.222.
[36]	HUANG B， LI X， ZHANG X. SWPanGAN： a hybrid generative adversarial network for pansharpening［J］. IET Image Processing， 2024， 18（8）： 1950-1966.
[37]	LIU Q， MENG X， SHAO F， et al. Supervised-unsupervised combined deep convolutional neural networks for high-fidelity pansharpening［J］. Information Fusion， 2023， 89： 292-304.
[38]	ZHOU H， LIU Q， WANG Y. PGMAN： an unsupervised generative multiadversarial network for pansharpening［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing， 2021， 14： 6316-6327.
[39]	NI J， SHAO Z， ZHANG Z， et al. LDP-Net： an unsupervised pansharpening network based on learnable degradation processes［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing， 2022， 15： 5468-5479.
[40]	WANG W， DENG L J， VIVONE G. A general image fusion framework using multi-task semi-supervised learning［J］. Information Fusion， 2024， 108： No.102414.
[41]	ALPARONE L， AIAZZI B， BARONTI S， et al. Multispectral and panchromatic data fusion assessment without reference［J］. Photogrammetric Engineering and Remote Sensing， 2008， 74（2）： 193-200.
[42]	WANG H， ZHANG H， TIAN X， et al. Zero-Sharpen： a universal pansharpening method across satellites for reducing scale-variance gap via zero-shot variation［J］. Information Fusion， 2024， 101： No.102003.

数据集	指标	PRACS	AWLP	MGF	TDNet	PAPS	MSDCNN	LDP-Net	PGMAN	TCONet	理想值
QB	SSIM	0.985 7	0.950 6	0.976 4	0.967 5	0.987 1	0.986 0	0.676 9	0.964 6	0.993 2	1
	PSNR/dB	48.876 2	47.499 1	47.002 6	44.765 0	47.881 8	47.860 4	31.122 0	46.138 3	50.613 7	+∞
	SAM	0.948 7	0.954 6	1.220 0	1.288 3	0.832 5	0.942 2	2.411 9	1.308 2	0.712 9	0
	ERGAS	0.665 5	0.772 2	0.991 9	1.053 2	0.624 2	0.668 6	3.397 8	1.063 6	0.465 0	0
	CC	0.993 8	0.994 2	0.990 7	0.990 0	0.995 6	0.994 6	0.970 8	0.988 4	0.997 0	1
WV-4	SSIM	0.959 4	0.949 4	0.954 1	0.948 5	0.966 7	0.965 0	0.781 8	0.941 5	0.978 7	1
	PSNR/dB	44.140 8	43.237 5	42.383 0	40.899 3	42.227 8	42.518 9	31.679 2	42.549 6	44.981 4	+∞
	SAM	2.082 6	2.975 0	2.483 1	1.964 5	1.790 9	1.771 5	3.357 2	2.235 7	1.521 9	0
	ERGAS	1.679 2	2.215 4	2.110 7	2.029 3	1.702 9	1.620 8	4.154 1	2.040 0	1.252 3	0
	CC	0.992 2	0.980 9	0.990 1	0.991 9	0.994 3	0.994 0	0.982 3	0.988 5	0.995 5	1
WV-2	SSIM	0.860 0	0.910 3	0.914 2	0.960 8	0.944 4	0.948 1	0.822 9	0.825 4	0.966 0	1
	PSNR/dB	31.708 9	32.283 6	32.431 3	35.440 5	33.891 4	33.894 6	28.842 2	30.278 9	36.113 4	+∞
	SAM	6.299 1	7.051 2	6.403 1	4.423 2	5.041 8	5.203 1	8.190 3	6.658 0	4.155 8	0
	ERGAS	4.955 8	4.738 6	4.464 8	2.959 2	3.435 3	3.685 0	5.827 6	5.729 3	2.751 5	0
	CC	0.905 8	0.898 0	0.918 1	0.953 6	0.942 2	0.939 9	0.872 4	0.894 4	0.958 5	1

数据集	指标	PRACS	AWLP	MGF	TDNet	PAPS	MSDCNN	LDP-Net	PGMAN	TCONet	理想值
QB	SSIM	0.985 7	0.950 6	0.976 4	0.967 5	0.987 1	0.986 0	0.676 9	0.964 6	0.993 2	1
	PSNR/dB	48.876 2	47.499 1	47.002 6	44.765 0	47.881 8	47.860 4	31.122 0	46.138 3	50.613 7	+∞
	SAM	0.948 7	0.954 6	1.220 0	1.288 3	0.832 5	0.942 2	2.411 9	1.308 2	0.712 9	0
	ERGAS	0.665 5	0.772 2	0.991 9	1.053 2	0.624 2	0.668 6	3.397 8	1.063 6	0.465 0	0
	CC	0.993 8	0.994 2	0.990 7	0.990 0	0.995 6	0.994 6	0.970 8	0.988 4	0.997 0	1
WV-4	SSIM	0.959 4	0.949 4	0.954 1	0.948 5	0.966 7	0.965 0	0.781 8	0.941 5	0.978 7	1
	PSNR/dB	44.140 8	43.237 5	42.383 0	40.899 3	42.227 8	42.518 9	31.679 2	42.549 6	44.981 4	+∞
	SAM	2.082 6	2.975 0	2.483 1	1.964 5	1.790 9	1.771 5	3.357 2	2.235 7	1.521 9	0
	ERGAS	1.679 2	2.215 4	2.110 7	2.029 3	1.702 9	1.620 8	4.154 1	2.040 0	1.252 3	0
	CC	0.992 2	0.980 9	0.990 1	0.991 9	0.994 3	0.994 0	0.982 3	0.988 5	0.995 5	1
WV-2	SSIM	0.860 0	0.910 3	0.914 2	0.960 8	0.944 4	0.948 1	0.822 9	0.825 4	0.966 0	1
	PSNR/dB	31.708 9	32.283 6	32.431 3	35.440 5	33.891 4	33.894 6	28.842 2	30.278 9	36.113 4	+∞
	SAM	6.299 1	7.051 2	6.403 1	4.423 2	5.041 8	5.203 1	8.190 3	6.658 0	4.155 8	0
	ERGAS	4.955 8	4.738 6	4.464 8	2.959 2	3.435 3	3.685 0	5.827 6	5.729 3	2.751 5	0
	CC	0.905 8	0.898 0	0.918 1	0.953 6	0.942 2	0.939 9	0.872 4	0.894 4	0.958 5	1

卫星	指标	PRACS	AWLP	MGF	TDNet	PAPS	MSDCNN	LDP-Net	PGMAN	TCONet	理想值
QB	D_λ	0.015 6	0.050 2	0.027 4	0.034 2	0.028 3	0.032 0	0.029 3	0.001 7	0.010 0	0
	D_s	0.023 8	0.061 7	0.031 9	0.031 8	0.048 9	0.029 3	0.090 8	0.018 4	0.007 7	0
	QNR	0.960 9	0.892 0	0.941 7	0.935 0	0.924 3	0.939 5	0.723 2	0.979 8	0.982 2	1
WV-4	D_λ	0.012 5	0.032 3	0.023 7	0.022 6	0.033 0	0.026 0	0.093 4	0.002 7	0.002 5	0
	D_s	0.023 2	0.042 9	0.039 3	0.026 3	0.050 0	0.049 0	0.081 3	0.020 8	0.011 6	0
	QNR	0.964 6	0.926 3	0.937 9	0.951 6	0.918 5	0.926 1	0.832 8	0.976 4	0.985 9	1
WV-2	D_λ	0.009 7	0.059 6	0.043 1	0.026 3	0.035 0	0.041 9	0.033 2	0.003 4	0.019 1	0
	D_s	0.030 7	0.044 4	0.045 6	0.031 1	0.051 9	0.046 9	0.062 3	0.040 5	0.012 2	0
	QNR	0.959 8	0.899 1	0.913 3	0.943 4	0.915 4	0.913 2	0.906 6	0.956 2	0.968 8	1

卫星	指标	PRACS	AWLP	MGF	TDNet	PAPS	MSDCNN	LDP-Net	PGMAN	TCONet	理想值
QB	D_λ	0.015 6	0.050 2	0.027 4	0.034 2	0.028 3	0.032 0	0.029 3	0.001 7	0.010 0	0
	D_s	0.023 8	0.061 7	0.031 9	0.031 8	0.048 9	0.029 3	0.090 8	0.018 4	0.007 7	0
	QNR	0.960 9	0.892 0	0.941 7	0.935 0	0.924 3	0.939 5	0.723 2	0.979 8	0.982 2	1
WV-4	D_λ	0.012 5	0.032 3	0.023 7	0.022 6	0.033 0	0.026 0	0.093 4	0.002 7	0.002 5	0
	D_s	0.023 2	0.042 9	0.039 3	0.026 3	0.050 0	0.049 0	0.081 3	0.020 8	0.011 6	0
	QNR	0.964 6	0.926 3	0.937 9	0.951 6	0.918 5	0.926 1	0.832 8	0.976 4	0.985 9	1
WV-2	D_λ	0.009 7	0.059 6	0.043 1	0.026 3	0.035 0	0.041 9	0.033 2	0.003 4	0.019 1	0
	D_s	0.030 7	0.044 4	0.045 6	0.031 1	0.051 9	0.046 9	0.062 3	0.040 5	0.012 2	0
	QNR	0.959 8	0.899 1	0.913 3	0.943 4	0.915 4	0.913 2	0.906 6	0.956 2	0.968 8	1

方法	SSIM	PSNR/dB	SAM	ERGAS	CC	D_λ	D_s	QNR
TCONet	0.993 2	50.613 7	0.712 9	0.465 0	0.997 0	0.010 0	0.007 7	0.982 2
w/o IMRA	0.988 6	47.420 0	1.097 2	0.713 7	0.994 5	0.018 8	0.017 7	0.963 8
w/o AM	0.987 6	47.991 9	0.939 2	0.638 7	0.994 3	0.012 0	0.020 5	0.967 7
w/o MFEM	0.916 0	38.839 1	1.757 3	1.565 9	0.985 0	0.035 4	0.040 5	0.925 5
w/o SIEN	0.976 1	45.128 4	1.317 3	0.890 5	0.990 3	0.018 1	0.020 4	0.961 8
PS	0.979 4	46.117 8	1.196 8	0.813 7	0.991 1	0.022 8	0.013 5	0.964 0
AIMMN	0.985 5	49.402 2	0.830 0	0.568 0	0.995 0	0.023 9	0.022 0	0.954 6
理想值	1	+∞	0	0	1	0	0	1

Pansharpening based on two-stage collaborative optimization

基于两阶段协同优化的全色锐化

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 15

References 42

Related Articles 15

Recommended Articles

Metrics

[1]	Xing SHENG, Sunxian WENG, Kuosong CHEN, Zhongping WANG, Ruifeng REN, Yong LIU. Deep learning-based patent value evaluation for power grid enterprises [J]. Journal of Computer Applications, 2026, 46(5): 1468-1474.
[2]	Yifan SUO, Songhua LIU, Qiuzhi HAO. Time series anomaly detection method based on high-order feature aggregation [J]. Journal of Computer Applications, 2026, 46(4): 1131-1138.
[3]	Jie HU, Pengcheng LI, Jun SUN, Jiaao ZHANG. Key phrase extraction model based on multi-perspective information enhancement and hierarchical weighting [J]. Journal of Computer Applications, 2026, 46(4): 1050-1057.
[4]	Chunyong YIN, Bufan ZHANG. Multi-scale based multivariate time series anomaly detection model [J]. Journal of Computer Applications, 2026, 46(3): 790-797.
[5]	Limei DONG, Yanzi LI, Jiayin LI, Li XU. Neighborhood-enhanced unsupervised graph anomaly detection [J]. Journal of Computer Applications, 2026, 46(2): 458-466.
[6]	Wen LI, Kairong LI, Kai YANG. Subgraph-aware contrastive learning with data augmentation [J]. Journal of Computer Applications, 2026, 46(1): 1-9.
[7]	Jin LI, Liqun LIU. SAR and visible image fusion based on residual Swin Transformer [J]. Journal of Computer Applications, 2025, 45(9): 2949-2956.
[8]	Panfeng JING, Yudong LIANG, Chaowei LI, Junru GUO, Jinyu GUO. Semi-supervised image dehazing algorithm based on teacher-student learning [J]. Journal of Computer Applications, 2025, 45(9): 2975-2983.
[9]	Chao LIU, Yanhua YU. Knowledge-aware recommendation model combining denoising strategy and multi-view contrastive learning [J]. Journal of Computer Applications, 2025, 45(9): 2827-2837.
[10]	Jin XIE, Surong CHU, Yan QIANG, Juanjuan ZHAO, Hua ZHANG, Yong GAO. Dual-branch distribution consistency contrastive learning model for hard negative sample identification in chest X-rays [J]. Journal of Computer Applications, 2025, 45(7): 2369-2377.
[11]	Yulin HE, Xu LI, Yingting HE, Laizhong CUI, Zhexue HUANG. Subspace Gaussian mixture model clustering ensemble algorithm based on maximum mean discrepancy [J]. Journal of Computer Applications, 2025, 45(6): 1712-1723.
[12]	Zonghang WU, Dong ZHANG, Guanyu LI. Multimodal fusion recommendation algorithm based on joint self-supervised learning [J]. Journal of Computer Applications, 2025, 45(6): 1858-1868.
[13]	Ying HUANG, Shengmei GAO, Guang CHEN, Su LIU. Low-light image enhancement network combining signal-to-noise ratio guided dual-branch structure and histogram equalization [J]. Journal of Computer Applications, 2025, 45(6): 1971-1979.
[14]	Pengyu CHEN, Xiushan NIE, Nanjun LI, Tuo LI. Semi-supervised video object segmentation method based on spatio-temporal decoupling and regional robustness enhancement [J]. Journal of Computer Applications, 2025, 45(5): 1379-1386.
[15]	Wenpeng WANG, Yinchang QIN, Wenxuan SHI. Review of unsupervised deep learning methods for industrial defect detection [J]. Journal of Computer Applications, 2025, 45(5): 1658-1670.