基于跨空间多尺度信息聚合和推理一致性的域泛化方法

黎拓新; 项凤涛; 陈君海; 张晓博; 吕云霄

doi:10.11959/j.issn.2096-6652.202516

您当前的位置：

首页 >

文章列表页 >

基于跨空间多尺度信息聚合和推理一致性的域泛化方法

学术论文 | 更新时间：2025-07-21

- 基于跨空间多尺度信息聚合和推理一致性的域泛化方法
- Domain generalization method based on cross-space multi-scale information aggregation and inference consistency
- 智能科学与技术学报 2025年7卷第2期页码：200-210
- 作者机构：
  
  国防科技大学智能科学学院，湖南长沙 410073
- 作者简介：
  
  [ "黎拓新（2002- ），男，国防科技大学智能科学学院硕士生，主要研究方向为模式识别、人工智能、迁移学习。" ]
  [ "项凤涛（1986- ），男，博士，国防科技大学智能科学学院副教授，主要研究方向为智能辅助决策、不确定性推理、智能控制。" ]
  [ "陈君海（2001- ），男，国防科技大学智能科学学院硕士生，主要研究方向为人工智能、谣言检测。" ]
  [ "张晓博（2002- ），男，国防科技大学智能科学学院硕士生，主要研究方向为人工智能、增量学习。" ]
  [ "吕云霄（1985- ），女，国防科技大学智能科学学院高级工程师、副处长，主要研究方向为导航技术。" ]
- 基金信息：
  
  国家自然科学基金项目(62473371)
- DOI：10.11959/j.issn.2096-6652.202516
  中图分类号： TP391.4
- 收稿日期：2025-01-21，
  
  修回日期：2025-04-11，
  
  纸质出版日期：2025-06-15
- 稿件说明：
移动端阅览
黎拓新,项凤涛,陈君海等.基于跨空间多尺度信息聚合和推理一致性的域泛化方法[J].智能科学与技术学报,2025,07(02):200-210.

LI Tuoxin,XIANG Fengtao,CHEN Junhai,et al.Domain generalization method based on cross-space multi-scale information aggregation and inference consistency[J].Chinese Journal of Intelligent Science and Technology,2025,07(02):200-210.
黎拓新,项凤涛,陈君海等.基于跨空间多尺度信息聚合和推理一致性的域泛化方法[J].智能科学与技术学报,2025,07(02):200-210. DOI： 10.11959/j.issn.2096-6652.202516.

LI Tuoxin,XIANG Fengtao,CHEN Junhai,et al.Domain generalization method based on cross-space multi-scale information aggregation and inference consistency[J].Chinese Journal of Intelligent Science and Technology,2025,07(02):200-210. DOI： 10.11959/j.issn.2096-6652.202516.

摘要

在机器学习中，通常模型假设训练数据和测试数据来自相同的分布，然而在实际应用中，数据分布往往存在差异，导致域漂移问题，进而影响模型的泛化能力。现有域泛化方法主要集中在提取域不变特征，忽视了域特定特征对模型预测的影响。为此，提出了一种基于跨空间多尺度信息聚合的域鉴别器，通过多尺度信息捕捉，有效去除域特定特征，增强域不变特征的提取能力；同时通过动量更新推理一致性损失函数，利用样本类别中心的推理一致性，进一步提高模型的鲁棒性。在多个公开数据集上进行了对比实验与分析，结果表明，新方法在域泛化中具有更好的性能表现，有效缓解了域特定特征对模型性能的影响，可为处理域漂移问题提供技术参考。

Abstract

In machine learning

it typically assumes that training data and testing data of models are drawn from the same distribution. However

in real-world applications

data distributions often differ

resulting in domain shift problems that adversely affect model generalization. Existing domain generalization methods primarily focus on extracting domain-invariant features while overlooking the potential impact of domain-specific features on model predictions. To address this issue

a domain discriminator based on cross-space multi-scale information aggregation was proposed. By capturing multi-scale information

domain-specific features were effectively removed and the extraction of domain-invariant features was enhanced. Additionally

the momentum update inference consistency loss function was employed to leverage the inference consistency of sample category centers

further improving model robustness. Comparative experiments and analysis conducted on multiple public datasets demonstrate that the proposed method exhibits superior performance in domain generalization

effectively mitigating the impact of domain-specific features on model performance and providing a technical reference for addressing domain shift problems.

关键词

Keywords

references

KOH P W, SAGAWA S, MARKLUND H, et al. Wilds: a benchmark of in-the-wild distribution shifts[C]//Proceedings of the International Conference on Machine Learning. New York: PMLR, 2021: 5637-5664.

PAN S J, YANG Q. A survey on transfer learning[J]. IEEE Transactions on Knowledge and Data Engineering, 2010, 22(10): 1345-1359.

YOU K C, LONG M S, CAO Z J, et al. Universal domain adaptation[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2019: 2720-2729.

HUANG D J, LI J C, CHEN W K, et al. Divide and adapt: active domain adaptation via customized learning[C]//Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2023: 7651-7660.

LI Z, CAI R, CHEN G, et al. Subspace identification for multi-source domain adaptation[J]. Advances in Neural Information Processing Systems, 2023, 36: 34504-34518.

李凤岐, 金佳玉, 杜学峰, 等. 基于域对抗自适应学习的旋翼无人机姿态稳定方法[J]. 自动化学报, 2025, 51: 1-15.

LI F Q, JIN J Y, DU X F, et al. Attitude stability method for rotor UAV based on domain adversarial self-adaptive learning[J]. Acta Automatica Sinica, 2025, 51: 1-15.

BLANCHARD G, LEE G, SCOTT C. Generalizing from several related classification tasks to a new unlabeled sample[C]//Proceedings of the 25th International Conference on Neural Information Processing Systems. Massachusetts: MIT Press, 2011: 2178-2186.

MUANDET K, BALDUZZI D, SCHÖLKOPF B. Domain generalization via invariant feature representation[C]//Proceedings of the International Conference on Machine Learning. New York: PMLR, 2013: 10-18.

DESHMUKH A, LEI Y W, SHARMA S, et al. A generalization error bound for multi-class domain generalization[EB]. 2019.

GILLES B, ANAND D A, URUN D, et al. Domain generalization by marginal transfer learning[J]. Journal of Machine Learning Research, 2021, 22(2): 1-55.

YE H, XIE C, CAI T, et al. Towards a theoretical framework of out-of-distribution generalization[J]. Advances in Neural Information Processing Systems, 2021, 34: 23519-23531.

CHEN L, ZHANG Y, SONG Y B, et al. Domain generalization via rationale invariance[C]//Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision (ICCV). Piscataway: IEEE Press, 2023: 1751-1760.

SAIN S R. The nature of statistical learning theory[J]. Technometrics, 1996, 38(4): 409.

VEDANTAM R, LOPEZ-PAZ D, SCHWAB D J. An empirical investigation of domain generalization with empirical risk minimizers[J]. Advances in Neural Information Processing Systems, 2021, 34: 28131-28143.

LI H L, PAN S J, WANG S Q, et al. Domain generalization with adversarial feature learning[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2018: 5400-5409.

MOTIIAN S, PICCIRILLI M, ADJEROH D A, et al. Unified deep supervised domain adaptation and generalization[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV). Piscataway: IEEE Press, 2017: 5716-5726.

LI Y, TIAN X, GONG M, et al. Deep domain generalization via conditional invariant adversarial networks[C]//Proceedings of the European Conference on Computer Vision (ECCV). Cham: Springer International Publishing, 2018: 624-639.

ARJOVSKY M, BOTTOU L, GULRAJANI I, et al. Invariant risk minimization[EB]. 2020.

GHIFARY M, KLEIJN W B, ZHANG M J, et al. Domain generalization for object recognition with multi-task autoencoders[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV). Piscataway: IEEE Press, 2015: 2551-2559.

MAHAJAN D, TOPLE S, SHARMA A. Domain generalization using causal matching[C]//Proceedings of the International Conference on Machine Learning. New York: PMLR, 2021: 7313-7324.

GUO J T, QI L, SHI Y H. DomainDrop: suppressing domain-sensitive channels for domain generalization[C]//Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision (ICCV). Piscataway: IEEE Press, 2023: 19057-19067.

倪云昊, 黄雷. 基于数据表示不变性的域泛化研究[J]. 图学学报, 2024, 45(4): 705-713.

NI Y H, HUANG L. Domain generalization based on data representation invariance[J]. Journal of Graphics, 2024, 45(4): 705-713.

ZHOU K Y, YANG Y X, HOSPEDALES T, et al. Deep domain-adversarial image generation for domain generalisation[C]//Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2020, 34(7): 13025-13032.

WANG Y, QI L, SHI Y H, et al. Feature-based style randomization for domain generalization[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2022, 32(8): 5495-5509.

ZHOU K Y, YANG Y X, QIAO Y, et al. Domain adaptive ensemble learning[J]. IEEE Transactions on Image Processing, 2021, 30: 8008-8018.

SEGU M, TONIONI A, TOMBARI F. Batch normalization embeddings for deep domain generalization[J]. Pattern Recognition, 2023, 135: 109115.

SEO S, SUH Y, KIM D, et al. Learning to optimize domain specific normalization for domain generalization[C]//Proceedings of the European Conference on Computer Vision (ECCV). Cham: Springer International Publishing, 2020: 68-83.

童煜钧, 王荷清, 罗悦恒, 等. 基于扩散模型数据增广的域泛化方法[J]. 智能科学与技术学报, 2023, 5(3): 380-388.

TONG Y J, WANG H Q, LUO Y H, et al. Domain generalization method based on diffusion model data augmentation[J]. Chinese Journal of Intelligent Science and Technology, 2023, 5(3): 380-388.

HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2018: 7132-7141.

WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision (ECCV). Cham: Springer International Publishing, 2018: 3-19.

OUYANG D, HE S, ZHANG G, et al. Efficient multi-scale attention module with cross-spatial learning[C]//Proceedings of the ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Piscataway: IEEE Press, 2023: 1-5.

LI D, YANG Y X, SONG Y Z, et al. Deeper, broader and artier domain generalization[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV). Piscataway: IEEE Press, 2017: 5543-5551.

TORRALBA A, EFROS A A. Unbiased look at dataset bias[C]//Proceedings of the CVPR 2011. Piscataway: IEEE Press, 2011: 1521-1528.

VENKATESWARA H, EUSEBIO J, CHAKRABORTY S, et al. Deep hashing network for unsupervised domain adaptation[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2017: 5385-5394.

HOU Q B, ZHOU D Q, FENG J S. Coordinate attention for efficient mobile network design[C]//Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2021: 13708-13717.

MATSUURA T, HARADA T. Domain generalization using a mixture of multiple latent domains[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(7): 11749-11756.

EFRAIMIDIS P S, SPIRAKIS P G. Weighted random sampling with a reservoir[J]. Information Processing Letters, 2006, 97(5): 181-185.

CARLUCCI F M, D'INNOCENTE A, BUCCI S, et al. Domain generalization by solving jigsaw puzzles[C]//Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2019: 2224-2233.

SHI B, ZHANG D, DAI Q, et al. Informative dropout for robust representation learning: a shape-bias perspective[C]//Proceedings of the International Conference on Machine Learning. New York: PMLR, 2020: 8828-8839.

DU D P, CHEN J W, LI Y X, et al. Cross-domain gated learning for domain generalization[J]. International Journal of Computer Vision, 2022, 130(11): 2842-2857.

CHATTOPADHYAY P, BALAJI Y, HOFFMAN J. Learning to balance specificity and invariance for in and out of domain generalization[C]//Proceedings of the European Conference on Computer Vision (ECCV). Cham: Springer International Publishing, 2020: 301-318.

RAME A, DANCETTE C, CORD M. Fishr: invariant gradient variances for out-of-distribution generalization[C]//Proceedings of the International Conference on Machine Learning. New York: PMLR, 2022: 18347-18377.

DING Y Z, WANG L, LIANG B X, et al. Domain generalization by learning and removing domain-specific features[J].Advances in Neural Information Processing Systems, 2022, 35: 24226-24239.

HUANG Z Y, WANG H H, XING E P, et al. Self-challenging improves cross-domain generalization[C]//Proceedings of the European Conference on Computer Vision (ECCV). Cham: Springer International Publishing, 2020: 124-140.

ZHOU K, YANG Y, QIAO Y, et al. Domain generalization with MixStyle[EB]. 2021.

ZHANG Y B, LI M H, LI R H, et al. Exact feature distribution matching for arbitrary style transfer and domain generalization[C]//Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2022: 8025-8035.

GUO J T, WANG N, QI L, et al. ALOFT: a lightweight MLP-like architecture with dynamic low-frequency transform for domain generalization[C]//Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2023: 24132-24141.

ZHANG X X, CUI P, XU R Z, et al. Deep stable learning for out-of-distribution generalization[C]//Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2021: 5372-5382.

XU Q W, ZHANG R P, ZHANG Y, et al. A Fourier-based framework for domain generalization[C]//Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2021: 14383-14392.

LI C M, ZHANG D A, HUANG W J, et al. Cross contrasting feature perturbation for domain generalization[C]//Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision (ICCV). Piscataway: IEEE Press, 2023: 1327-1337.

SHI Z, MING Y, FAN Y, et al. Domain generalization via nuclear norm regularization[C]//Proceedings of the Conference on Parsimony and Learning. New York: PMLR, 2024: 179-201.

LONG S C, ZHOU Q Y, YING C H, et al. Rethinking domain generalization: discriminability and generalizability[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2024, 34(11): 11783-11797.

NAM H, LEE H, PARK J, et al. Reducing domain gap by reducing style bias[C]//Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2021: 8686-8695.

CHA J, CHUN S, LEE K, et al. Swad: domain generalization by seeking flat minima[J]. Advances in Neural Information Processing Systems, 2021, 34: 22405-22418.

SELVARAJU R R, COGSWELL M, DAS A, et al. Grad-CAM: visual explanations from deep networks via gradient-based localization[C]//Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV). Piscataway: IEEE Press, 2017: 618-626.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

HCANet：基于分层Transformer架构的微表情识别模型

基于自适应池化注意力Transformer的唇语识别方法

注意力机制增强的输煤传送带异物检测

融合句法增强与语义增强的方面情感分析

基于改进YOLOv5s的小人脸检测