《计算机应用》唯一官方网站 ›› 2025, Vol. 45 ›› Issue (10): 3371-3380.DOI: 10.11772/j.issn.1001-9081.2024101442
• 前沿与综合应用 • 上一篇
收稿日期:
2024-10-11
修回日期:
2024-12-30
接受日期:
2024-12-31
发布日期:
2025-01-06
出版日期:
2025-10-10
通讯作者:
陈庆锋
作者简介:
王一铭(2000—),男,广西南宁人,硕士研究生,主要研究方向:医学图像处理、可信机器学习、数据挖掘基金资助:
Yiming WANG1, Shiyuan LI1, Nanqing LIAO2, Qingfeng CHEN1()
Received:
2024-10-11
Revised:
2024-12-30
Accepted:
2024-12-31
Online:
2025-01-06
Published:
2025-10-10
Contact:
Qingfeng CHEN
About author:
WANG Yiming, born in 2000, M. S. candidate. His research interests include medical image processing, trustworthy machine learning, data mining.Supported by:
摘要:
医学图像配准中的不确定性量化对医师在实际临床应用中评估风险至关重要。目前,基于深度无监督学习的医学图像配准模型虽然已经具备不错的效果,但仍缺乏在配准时估计外观不确定性的方法,这将影响配准的精度和可信度。此外,在实时性应用场景中,医学图像配准模型不但需要具备较高的配准精度,还需要快速进行推理。针对上述问题,提出一种基于证据深度学习(EDL)的不确定性感知无监督医学图像配准模型EvidentialMorph,将EDL应用于无监督医学图像配准。EDL是一种不确定性量化方法,无需额外的计算开销。首先,通过U-net架构的配准主干网络模块学习得到形变向量场(DVF);其次,通过一种改进的空间变换器网络(STN)模块——证据STN模块学习配准图像的正态逆伽马(NIG)分布,从而直接计算出配准图像及其外观不确定性。在海马体、LPBA40和IBSR18核磁共振成像(MRI)数据集上的实验结果表明,与CLMorph模型相比,在配准精度上,EvidentialMorph的Dice相似性系数(DSC)最高提升了3.31%,归一化交叉相关(NCC)系数最高提升了2.75%;在推理时耗上,EvidentialMorph减少了85 ms。以上结果验证了EvidentialMorph能够快速得到有效的不确定性量化结果,并提升配准精度,为实时医学图像配准场景提供了不确定性量化的可能,可以改善配准效果。
中图分类号:
王一铭, 李世源, 廖南清, 陈庆锋. 基于证据深度学习的不确定性感知无监督医学图像配准模型[J]. 计算机应用, 2025, 45(10): 3371-3380.
Yiming WANG, Shiyuan LI, Nanqing LIAO, Qingfeng CHEN. Uncertainty-aware unsupervised medical image registration model based on evidential deep learning[J]. Journal of Computer Applications, 2025, 45(10): 3371-3380.
模型 | 海马体 | LPBA40 | IBSR18 | ||||||
---|---|---|---|---|---|---|---|---|---|
DSC | NCC | MSE | DSC | NCC | MSE | DSC | NCC | MSE | |
集成 | 0.745 | 0.889 | 0.004 44 | 0.570 | 0.904 | 0.002 27 | 0.820 | 0.903 | 0.005 40 |
MC dropout | 0.707 | 0.878 | 0.005 08 | 0.532 | 0.890 | 0.001 80 | 0.497 | 0.887 | 0.006 69 |
Snapshot | 0.746 | 0.823 | 0.010 19 | 0.561 | 0.870 | 0.007 16 | 0.783 | 0.784 | 0.021 51 |
CCI | 0.751 | 0.889 | 0.004 07 | 0.576 | 0.905 | 0.001 80 | 0.825 | 0.903 | 0.005 31 |
DP | 0.737 | 0.888 | 0.004 52 | 0.569 | 0.895 | 0.001 77 | 0.802 | 0.898 | 0.005 66 |
CLMorph | 0.752 | 0.890 | 0.004 35 | 0.605 | 0.906 | 0.001 92 | 0.827 | 0.910 | 0.003 52 |
MNDVF | 0.746 | 0.886 | 0.005 14 | 0.572 | 0.903 | 0.002 35 | 0.821 | 0.902 | 0.005 37 |
EvidentialMorph | 0.754 | 0.891 | 0.004 06 | 0.625 | 0.912 | 0.001 72 | 0.843 | 0.935 | 0.002 31 |
表1 不同模型无监督配准性能的比较
Tab. 1 Comparison of unsupervised registration performance of different models
模型 | 海马体 | LPBA40 | IBSR18 | ||||||
---|---|---|---|---|---|---|---|---|---|
DSC | NCC | MSE | DSC | NCC | MSE | DSC | NCC | MSE | |
集成 | 0.745 | 0.889 | 0.004 44 | 0.570 | 0.904 | 0.002 27 | 0.820 | 0.903 | 0.005 40 |
MC dropout | 0.707 | 0.878 | 0.005 08 | 0.532 | 0.890 | 0.001 80 | 0.497 | 0.887 | 0.006 69 |
Snapshot | 0.746 | 0.823 | 0.010 19 | 0.561 | 0.870 | 0.007 16 | 0.783 | 0.784 | 0.021 51 |
CCI | 0.751 | 0.889 | 0.004 07 | 0.576 | 0.905 | 0.001 80 | 0.825 | 0.903 | 0.005 31 |
DP | 0.737 | 0.888 | 0.004 52 | 0.569 | 0.895 | 0.001 77 | 0.802 | 0.898 | 0.005 66 |
CLMorph | 0.752 | 0.890 | 0.004 35 | 0.605 | 0.906 | 0.001 92 | 0.827 | 0.910 | 0.003 52 |
MNDVF | 0.746 | 0.886 | 0.005 14 | 0.572 | 0.903 | 0.002 35 | 0.821 | 0.902 | 0.005 37 |
EvidentialMorph | 0.754 | 0.891 | 0.004 06 | 0.625 | 0.912 | 0.001 72 | 0.843 | 0.935 | 0.002 31 |
模型 | 海马体 | LPBA40 | IBSR18 | ||||||
---|---|---|---|---|---|---|---|---|---|
DSC | NCC | MSE | DSC | NCC | MSE | DSC | NCC | MSE | |
集成 | 0.746 | 0.889 | 0.004 46 | 0.573 | 0.905 | 0.002 52 | 0.826 | 0.903 | 0.005 28 |
MC dropout | 0.708 | 0.881 | 0.004 34 | 0.534 | 0.890 | 0.002 97 | 0.502 | 0.892 | 0.006 57 |
Snapshot | 0.753 | 0.821 | 0.009 36 | 0.569 | 0.855 | 0.007 96 | 0.783 | 0.784 | 0.021 13 |
CCI | 0.751 | 0.891 | 0.003 92 | 0.582 | 0.905 | 0.002 43 | 0.828 | 0.904 | 0.005 21 |
DP | 0.740 | 0.889 | 0.004 47 | 0.570 | 0.901 | 0.003 08 | 0.803 | 0.901 | 0.005 41 |
CLMorph | 0.758 | 0.892 | 0.004 06 | 0.607 | 0.910 | 0.002 02 | 0.830 | 0.912 | 0.003 32 |
MNDVF | 0.746 | 0.889 | 0.004 78 | 0.574 | 0.907 | 0.002 61 | 0.822 | 0.902 | 0.005 28 |
EvidentialMorph | 0.763 | 0.895 | 0.003 79 | 0.627 | 0.929 | 0.001 38 | 0.846 | 0.936 | 0.002 19 |
表2 不同模型半监督配准性能的比较
Tab. 2 Comparison of semi-supervised registration performance of different models
模型 | 海马体 | LPBA40 | IBSR18 | ||||||
---|---|---|---|---|---|---|---|---|---|
DSC | NCC | MSE | DSC | NCC | MSE | DSC | NCC | MSE | |
集成 | 0.746 | 0.889 | 0.004 46 | 0.573 | 0.905 | 0.002 52 | 0.826 | 0.903 | 0.005 28 |
MC dropout | 0.708 | 0.881 | 0.004 34 | 0.534 | 0.890 | 0.002 97 | 0.502 | 0.892 | 0.006 57 |
Snapshot | 0.753 | 0.821 | 0.009 36 | 0.569 | 0.855 | 0.007 96 | 0.783 | 0.784 | 0.021 13 |
CCI | 0.751 | 0.891 | 0.003 92 | 0.582 | 0.905 | 0.002 43 | 0.828 | 0.904 | 0.005 21 |
DP | 0.740 | 0.889 | 0.004 47 | 0.570 | 0.901 | 0.003 08 | 0.803 | 0.901 | 0.005 41 |
CLMorph | 0.758 | 0.892 | 0.004 06 | 0.607 | 0.910 | 0.002 02 | 0.830 | 0.912 | 0.003 32 |
MNDVF | 0.746 | 0.889 | 0.004 78 | 0.574 | 0.907 | 0.002 61 | 0.822 | 0.902 | 0.005 28 |
EvidentialMorph | 0.763 | 0.895 | 0.003 79 | 0.627 | 0.929 | 0.001 38 | 0.846 | 0.936 | 0.002 19 |
模型 | GPU | CPU | ||
---|---|---|---|---|
采样数 | 推理时耗/s | 采样数 | 推理时耗/s | |
集成 | 2 | 0.052 0 | 2 | 0.279 |
5 | 0.130 6 | 5 | 0.721 | |
10 | 0.261 1 | 10 | 1.457 | |
MC dropout | 2 | 0.019 2 | 2 | 0.302 |
5 | 0.038 9 | 5 | 0.682 | |
10 | 0.088 2 | 10 | 1.321 | |
Snapshot | 2 | 0.020 9 | 2 | 0.318 |
5 | 0.059 4 | 5 | 0.707 | |
10 | 0.108 0 | 10 | 1.465 | |
CCI | — | 0.022 8 | — | 0.333 |
DP | 2 | 0.023 9 | 2 | 0.298 |
5 | 0.052 8 | 5 | 0.685 | |
10 | 0.097 9 | 10 | 1.432 | |
CLMorph | — | 0.021 4 | — | 0.297 |
MNDVF | — | 0.030 1 | — | 0.366 |
EvidentialMorph | — | 0.016 5 | — | 0.212 |
表3 不同模型的推理时耗比较
Tab. 3 Comparison of inference time of different models
模型 | GPU | CPU | ||
---|---|---|---|---|
采样数 | 推理时耗/s | 采样数 | 推理时耗/s | |
集成 | 2 | 0.052 0 | 2 | 0.279 |
5 | 0.130 6 | 5 | 0.721 | |
10 | 0.261 1 | 10 | 1.457 | |
MC dropout | 2 | 0.019 2 | 2 | 0.302 |
5 | 0.038 9 | 5 | 0.682 | |
10 | 0.088 2 | 10 | 1.321 | |
Snapshot | 2 | 0.020 9 | 2 | 0.318 |
5 | 0.059 4 | 5 | 0.707 | |
10 | 0.108 0 | 10 | 1.465 | |
CCI | — | 0.022 8 | — | 0.333 |
DP | 2 | 0.023 9 | 2 | 0.298 |
5 | 0.052 8 | 5 | 0.685 | |
10 | 0.097 9 | 10 | 1.432 | |
CLMorph | — | 0.021 4 | — | 0.297 |
MNDVF | — | 0.030 1 | — | 0.366 |
EvidentialMorph | — | 0.016 5 | — | 0.212 |
模型 | 无监督配准 | 半监督配准 | ||||
---|---|---|---|---|---|---|
DSC | NCC | MSE | DSC | NCC | MSE | |
w/o Evidential | 0.569 | 0.904 | 0.001 87 | 0.572 | 0.905 | 0.003 12 |
w/o LESIM | 0.578 | 0.891 | 0.002 95 | 0.617 | 0.893 | 0.002 33 |
w/o STN | 0.102 | 0.173 | 0.169 15 | 0.103 | 0.231 | 0.167 81 |
EvidentialMorph | 0.625 | 0.912 | 0.001 72 | 0.627 | 0.929 | 0.001 38 |
表4 无监督配准和半监督配准的消融实验结果
Tab. 4 Ablation experimental results of unsupervised registration and semi-supervised registration
模型 | 无监督配准 | 半监督配准 | ||||
---|---|---|---|---|---|---|
DSC | NCC | MSE | DSC | NCC | MSE | |
w/o Evidential | 0.569 | 0.904 | 0.001 87 | 0.572 | 0.905 | 0.003 12 |
w/o LESIM | 0.578 | 0.891 | 0.002 95 | 0.617 | 0.893 | 0.002 33 |
w/o STN | 0.102 | 0.173 | 0.169 15 | 0.103 | 0.231 | 0.167 81 |
EvidentialMorph | 0.625 | 0.912 | 0.001 72 | 0.627 | 0.929 | 0.001 38 |
[1] | FU Y, LEI Y, WANG T, et al. Deep learning in medical image registration: a review[J]. Physics in Medicine and Biology, 2020, 65(20): No.20TR01. |
[2] | BIERBRIER J, GUEZIRI H E, COLLINS D L. Estimating medical image registration error and confidence: a taxonomy and scoping review[J]. Medical Image Analysis, 2022, 81: No.102531. |
[3] | CHEN J, LIU Y, WEI S, et al. A survey on deep learning in medical image registration: new technologies, uncertainty, evaluation metrics, and beyond[J]. Medical Image Analysis, 2025, 100: No.103385. |
[4] | DALCA A V, BALAKRISHNAN G, GUTTAG J, et al. Unsupervised learning of probabilistic diffeomorphic registration for images and surfaces[J]. Medical Image Analysis, 2019, 57: 226-236. |
[5] | KHAWALED S, FREIMAN M. Unsupervised deep-learning based deformable image registration: a Bayesian framework[EB/OL]. [2024-12-25].. |
[6] | LUO J, SEDGHI A, POPURI K, et al. On the applicability of registration uncertainty[C]// Proceedings of the 2019 Medical Image Computing and Computer-Assisted Intervention, LNCS 11765. Cham: Springer, 2019: 410-419. |
[7] | LUO J, FRISKEN S, WANG D, et al. Are registration uncertainty and error monotonically associated?[C]// Proceedings of the 2020 International Conference on Medical Image Computing and Computer-Assisted Intervention, LNCS 12263. Cham: Springer, 2020: 264-274. |
[8] | GONG X, KHAIDEM L, ZHU W, et al. Uncertainty learning towards unsupervised deformable medical image registration[C]// Proceedings of the 2022 IEEE/CVF Winter Conference on Applications of Computer Vision. Piscataway: IEEE, 2022: 1555-1564. |
[9] | KREBS J, MANSI T, DELINGETTE H, et al. Robust non-rigid registration through agent-based action learning[C]// Proceedings of the 2017 International Conference on Medical Image Computing and Computer-Assisted Intervention, LNCS 10433. Cham: Springer, 2017: 344-352. |
[10] | EPPENHOF K A J, LAFARGE M W, MOESKOPS P, et al. Deformable image registration using convolutional neural networks[C]// Proceedings of the SPIE 10574, Medical Imaging 2018: Image Processing. Bellingham, WA: SPIE, 2018: No.105740S. |
[11] | LIU Z, CHEN Q, LAN W, et al. SSLDTI: a novel method for drug-target interaction prediction based on self-supervised learning[J]. Artificial Intelligence in Medicine, 2024, 149: No.102778. |
[12] | BALAKRISHNAN G, ZHAO A, SABUNCU M R, et al. An unsupervised learning model for deformable medical image registration[C]// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2018: 9252-9260. |
[13] | BALAKRISHNAN G, ZHAO A, SABUNCU M R, et al. VoxelMorph: a learning framework for deformable medical image registration[J]. IEEE Transactions on Medical Imaging, 2019, 38(8): 1788-1800. |
[14] | RONNEBERGER O, FISCHER P, BROX T. U-net: convolutional networks for biomedical image segmentation[C]// Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention, LNCS 9351. Cham: Springer, 2015: 234-241. |
[15] | 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. |
[16] | HOOPES A, HOFFMANN M, FISCHL B, et al. HyperMorph: amortized hyperparameter learning for image registration[C]// Proceedings of the 2021 International Conference on Information Processing in Medical Imaging, LNCS 12729. Cham: Springer, 2021: 3-17. |
[17] | HOFFMANN M, BILLOT B, GREVE D N, et al. SynthMorph: learning contrast-invariant registration without acquired images[J]. IEEE Transactions on Medical Imaging, 2022, 41(3): 543-558. |
[18] | KIM B, KIM D H, PARK S H, et al. CycleMorph: cycle consistent unsupervised deformable image registration[J]. Medical Image Analysis, 2021, 71: No.102036. |
[19] | CHEN J, FREY E C, HE Y, et al. TransMorph: Transformer for unsupervised medical image registration[J]. Medical Image Analysis, 2022, 82: No.102615. |
[20] | 蒋宏贵,胡冀苏,钱旭升,等. 基于联合学习和多级小波金字塔的MRI-TRUS图像配准方法[J/OL]. 计算机工程 [2024-12-25].. |
JIANG H G, HU J S, QIAN X S, et al. Registration method of MRI-TRUS images based on joint learning and multi-level wavelet pyramid[J/OL]. Computer Engineering [2024-12-25].. | |
[21] | GAWLIKOWSKI J, TASSI C R N, ALI M, et al. A survey of uncertainty in deep neural networks[J]. Artificial Intelligence Review, 2023, 56(S1): 1513-1589. |
[22] | ZOU K, CHEN Z, YUAN X, et al. A review of uncertainty estimation and its application in medical imaging[J]. Meta-Radiology, 2023, 1(1): No.100003. |
[23] | BLUNDELL C, CORNEBISE J, KAVUKCUOGLU K, et al. Weight uncertainty in neural network[C]// Proceedings of the 32nd International Conference on Machine Learning. New York: JMLR.org, 2015: 1613-1622. |
[24] | KINGMA D P, SALIMANS T, WELLING M. Variational dropout and the local reparameterization trick[C]// Proceedings of the 29th International Conference on Neural Information Processing Systems — Volume 2. Cambridge: MIT Press, 2015: 2575-2583. |
[25] | GAL Y, GHAHRAMANI Z. Dropout as a Bayesian approximation: representing model uncertainty in deep learning[C]// Proceedings of the 33rd International Conference on Machine Learning. New York: JMLR.org, 2016: 1050-1059. |
[26] | BISHOP C M. Pattern recognition and machine learning[M]. New York: Springer, 2006. |
[27] | LAKSHMINARAYANAN B, PRITZEL A, BLUNDELL C. Simple and scalable predictive uncertainty estimation using deep ensembles[C]// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2017: 6405-6416. |
[28] | WANG G, LI W, AERTSEN M, et al. Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks[J]. Neurocomputing, 2019, 338: 34-45. |
[29] | AYHAN M S, BERENS P. Test-time data augmentation for estimation of heteroscedastic aleatoric uncertainty in deep neural networks[EB/OL]. [2024-09-11].. |
[30] | SENSOY M, KAPLAN L, KANDEMIR M. Evidential deep learning to quantify classification uncertainty[C]// Proceedings of the 32nd International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2018: 3183-3193. |
[31] | AMINI A, SCHWARTING W, SOLEIMANY A, et al. Deep evidential regression[C]// Proceedings of the 34th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2020: 14927-14937. |
[32] | LI S, CHEN Q, LIU Z, et al. Bi-SGTAR: a simple yet efficient model for circRNA-disease association prediction based on known association pair only[J]. Knowledge-Based Systems, 2024, 291: No.111622. |
[33] | SUDARSHAN V P, UPADHYAY U, EGAN G F, et al. Towards lower-dose PET using physics-based uncertainty-aware multimodal learning with robustness to out-of-distribution data[J]. Medical Image Analysis, 2021, 73: No.102187. |
[34] | XU Z, LUO J, LU D, et al. Double-uncertainty guided spatial and temporal consistency regularization weighting for learning-based abdominal registration[C]// Proceedings of the 2022 International Conference on Medical Image Computing and Computer-Assisted Intervention, LNCS 13436. Cham: Springer, 2022: 14-24. |
[35] | KWON Y, WON J H, KIM B J, et al. Uncertainty quantification using Bayesian neural networks in classification: application to biomedical image segmentation[J]. Computational Statistics and Data Analysis, 2020, 142: No.106816. |
[36] | RUAN Y, LI D, MARSHALL H, et al. Mt-UcGAN: multi-task uncertainty-constrained GAN for joint segmentation, quantification and uncertainty estimation of renal tumors on CT[C]// Proceedings of the 2020 International Conference on Medical Image Computing and Computer-Assisted Intervention, LNCS 12264. Cham: Springer, 2020: 439-449. |
[37] | CAO X, CHEN H, LI Y, et al. Uncertainty aware temporal-ensembling model for semi-supervised ABUS mass segmentation[J]. IEEE Transactions on Medical Imaging, 2021, 40(1): 431-443. |
[38] | LINMANS J, ELFWING S, VAN DER LAAK J, et al. Predictive uncertainty estimation for out-of-distribution detection in digital pathology[J]. Medical Image Analysis, 2023, 83: No.102655. |
[39] | FENG M, XU K, WU N, et al. Trusted multi-scale classification framework for whole slide image[J]. Biomedical Signal Processing and Control, 2024, 89: No.105790. |
[40] | ZOU K, YUAN X, SHEN X, et al. TBraTS: trusted brain tumor segmentation[C]// Proceedings of the 2022 International Conference on Medical Image Computing and Computer-Assisted Intervention, LNCS 13438. Cham: Springer, 2022: 503-513. |
[41] | LI S, LIU Y, CHEN Q, et al. Noise-resilient unsupervised graph representation learning via multi-hop feature quality estimation[C]// Proceedings of the 33rd ACM International Conference on Information and Knowledge Management. New York: ACM, 2024: 1255-1265. |
[42] | SIMPSON A L, ANTONELLI M, BAKAS S, et al. A large annotated medical image dataset for the development and evaluation of segmentation algorithms[EB/OL]. [2024-12-25].. |
[43] | SHATTUCK D W, MIRZA M, ADISETIYO V, et al. Construction of a 3D probabilistic atlas of human cortical structures[J]. NeuroImage, 2008, 39(3): 1064-1080. |
[44] | NeuroImaging Tools and Resources Collaboratory (NITRC). Internet Brain Segmentation Repository (IBSR)[DS/OL]. [2024-12-25].. |
[45] | HUANG G, LI Y, PLEISS G, et al. Snapshot ensembles: train 1, get M for free[EB/OL]. [2024-12-25].. |
[46] | VAN HARTEN L D, STOKER J, IŠGUM I. Robust deformable image registration using cycle-consistent implicit representations[J]. IEEE Transactions on Medical Imaging, 2024, 43(2): 784-793. |
[47] | ZHOU Z, YIN P, LIU Y, et al. Uncertain prediction of deformable image registration on lung CT using multi-category features and supervised learning[J]. Medical and Biological Engineering and Computing, 2024, 62(9): 2669-2686. |
[48] | LIU L, AVILES-RIVERO A I, SCHÖNLIEB C B. Contrastive registration for unsupervised medical image segmentation[J]. IEEE Transactions on Neural Networks and Learning Systems, 2025, 36(1): 147-159. |
[49] | RIVETTI L, STUDEN A, SHARMA M, et al. Uncertainty estimation and evaluation of deformation image registration based convolutional neural networks[J]. Physics in Medicine and Biology, 2024, 69(11): No.115045. |
[1] | 何玉林, 李旭, 贺颖婷, 崔来中, 黄哲学. 基于最大均值差异的子空间高斯混合模型聚类集成算法[J]. 《计算机应用》唯一官方网站, 2025, 45(6): 1712-1723. |
[2] | 黄颖, 高胜美, 陈广, 刘苏. 结合信噪比引导的双分支结构和直方图均衡的低照度图像增强网络[J]. 《计算机应用》唯一官方网站, 2025, 45(6): 1971-1979. |
[3] | 王文鹏, 秦寅畅, 师文轩. 工业缺陷检测无监督深度学习方法综述[J]. 《计算机应用》唯一官方网站, 2025, 45(5): 1658-1670. |
[4] | 潘理虎, 彭守信, 张睿, 薛之洋, 毛旭珍. 面向运动前景区域的视频异常检测[J]. 《计算机应用》唯一官方网站, 2025, 45(4): 1300-1309. |
[5] | 安俊秀, 杨林旺, 柳源. 基于邻近性语义感知的无监督文本风格迁移[J]. 《计算机应用》唯一官方网站, 2025, 45(4): 1139-1147. |
[6] | 贾洁茹, 杨建超, 张硕蕊, 闫涛, 陈斌. 基于自蒸馏视觉Transformer的无监督行人重识别[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2893-2902. |
[7] | 周妍, 李阳. 用于脑卒中病灶分割的具有注意力机制的校正交叉伪监督方法[J]. 《计算机应用》唯一官方网站, 2024, 44(6): 1942-1948. |
[8] | 夏吾吉, 黄鹤鸣, 更藏措毛, 范玉涛. 基于无监督学习和监督学习的抽取式文本摘要综述[J]. 《计算机应用》唯一官方网站, 2024, 44(4): 1035-1048. |
[9] | 江锐, 刘威, 陈成, 卢涛. 非对称端到端的无监督图像去雨网络[J]. 《计算机应用》唯一官方网站, 2024, 44(3): 922-930. |
[10] | 胡能兵, 蔡彪, 李旭, 曹旦华. 基于图池化对比学习的图分类方法[J]. 《计算机应用》唯一官方网站, 2024, 44(11): 3327-3334. |
[11] | 赵培, 乔焰, 胡荣耀, 袁新宇, 李敏悦, 张本初. 基于多域特征提取的多变量时间序列异常检测[J]. 《计算机应用》唯一官方网站, 2024, 44(11): 3419-3426. |
[12] | 黄梦林, 段磊, 张袁昊, 王培妍, 李仁昊. 基于Prompt学习的无监督关系抽取模型[J]. 《计算机应用》唯一官方网站, 2023, 43(7): 2010-2016. |
[13] | 许喆, 王志宏, 单存宇, 孙亚茹, 杨莹. 基于重构误差的无监督人脸伪造视频检测[J]. 《计算机应用》唯一官方网站, 2023, 43(5): 1571-1577. |
[14] | 葛孟婷, 万鸣华. 基于近邻监督局部不变鲁棒主成分分析的特征提取模型[J]. 《计算机应用》唯一官方网站, 2023, 43(4): 1013-1020. |
[15] | 王昊, 王子成, 张超, 马韵升. 基于生成对抗网络的数据不确定性量化方法[J]. 《计算机应用》唯一官方网站, 2023, 43(4): 1094-1101. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||