基于过渡桥接机制的对抗性开放集领域自适应

doi:10.19678/j.issn.1000-3428.0069878

计算机工程 ›› 2026, Vol. 52 ›› Issue (1): 116-125. doi: 10.19678/j.issn.1000-3428.0069878

基于过渡桥接机制的对抗性开放集领域自适应

田青¹^,²^,³^,*(), 郁江森¹, 刘祥¹, 李燕芝¹, 申珺妤¹

1. 南京信息工程大学软件学院, 江苏南京 210044
2. 南京信息工程大学无锡研究院, 江苏无锡 214000
3. 南京航空航天大学模式分析与机器智能工业和信息化部重点实验室, 江苏南京 211106

收稿日期:2024-05-21 修回日期:2024-07-13 出版日期:2026-01-15 发布日期:2024-09-27
通讯作者: 田青
作者简介:
田青(CCF高级会员), 男, 教授、博士、博士生导师, 主研方向为机器学习、模式识别、计算机视觉
郁江森, 硕士研究生
刘祥, 硕士研究生
李燕芝, 硕士研究生
申珺妤, 硕士研究生
基金资助:
国家自然科学基金(62176128); 江苏省自然科学基金(BK20231143); 中央高校基本科研业务费专项资金(NJ2023032); 江苏省"青蓝工程"人才计划项目

Adversarial Open-Set Domain Adaptation via Transition Bridge Mechanism

TIAN Qing¹^,²^,³^,*(), YU Jiangsen¹, LIU Xiang¹, LI Yanzhi¹, SHEN Junyu¹

1. School of Software, Nanjing University of Information Science and Technology, Nanjing 210044, Jiangsu, China
2. Wuxi Research Institute, Nanjing University of Information Science and Technology, Wuxi 214000, Jiangsu, China
3. MIIT Key Laboratory of Pattern Analysis and Machine Intelligence, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, Jiangsu, China

Received:2024-05-21 Revised:2024-07-13 Online:2026-01-15 Published:2024-09-27
Contact: TIAN Qing

摘要/Abstract

摘要：

无监督领域自适应(UDA)的目的是将知识从带有标记样本的源域转移到没有标记样本的目标域, 其假设源域和目标域具有相同的类别, 但这一假设在现实世界场景下往往难以成立。目标域通常包含着源域未被发现的新类别样本, 这种设置称为开放集领域自适应(OSDA)。在OSDA中, 丰富的域特定特征使得学习域不变表示面临着巨大挑战。现有的OSDA方法往往忽略了域特定特征, 并将域差异直接进行最小化, 这可能导致类别之间的边界不清晰并削弱模型的泛化能力。为了解决这一问题, 提出一种基于过渡桥接机制的OSDA方法(OSTBM)。在特征提取器和域鉴别器上建立过渡桥接机制, 以减少域特定特征在整体传递过程中的干扰, 并提高域鉴别器的鉴别能力, 从而在特征对齐过程中更好地对源分布与目标已知分布进行对齐, 并将目标未知分布推离决策边界。实验结果表明, 所提方法在多个基准数据集上表现优于现有的OSDA方法, 展现了优越的性能。

关键词: 领域自适应, 迁移学习, 开放集识别, 过渡桥接机制, 对抗学习

Abstract:

Unsupervised Domain Adaptation (UDA) aims to transfer knowledge from a source domain with labeled samples to a target domain without labeled samples. UDA assumes that the source and target domains have the same categories, which is often challenging to achieve in real-world scenarios. The target domain usually contains new categories of samples that are not found in the source domain, this setup is called Open-Set Domain Adaptation (OSDA). In OSDA, the abundance of domain-specific features makes learning domain-invariant representations a significant challenge. Existing OSDA methods tend to ignore domain-specific features and directly minimize domain differences, which may lead to unclear boundaries between categories and weaken the generalization ability of the model. To address this problem, the OSDA method based on a Transition Bridge Mechanism (OSTBM) is proposed. Specifically, the OSTBM adds a transition bridging mechanism to the feature extractor and domain discriminator to reduce the interference of domain-specific features in the overall transfer process and improves the discriminative ability of the domain discriminator. This enables better alignment of the source distribution with the known target distribution in the feature alignment process and pushes the unknown target distribution away from the decision boundary. The experimental results show that the proposed method outperforms existing OSDA methods on multiple benchmark datasets, demonstrating its superior performance.

Key words: domain adaptation, transfer learning, open-set recognition, transition bridge mechanism, adversarial learning

田青, 郁江森, 刘祥, 李燕芝, 申珺妤. 基于过渡桥接机制的对抗性开放集领域自适应[J]. 计算机工程, 2026, 52(1): 116-125.

TIAN Qing, YU Jiangsen, LIU Xiang, LI Yanzhi, SHEN Junyu. Adversarial Open-Set Domain Adaptation via Transition Bridge Mechanism[J]. Computer Engineering, 2026, 52(1): 116-125.

https://www.ecice06.com/CN/Y2026/V52/I1/116

图/表 8

图1 OSTBM方法的整体框架

Fig.1 The overall framework of the OSTBM method

图2 OSTBM不同领域适应阶段数据分布

Fig.2 Distribution of data at different stages of domain adaptation in OSTBM

图3 D→W任务上t-SNE可视化

Fig.3 t-SNE visualization on D→W task

图4 W→A任务上不同开放度下r_HOS结果

Fig.4 r_HOS results with different openness on the W→A task

参考文献 47

1	TIAN Q , ZHU Y N , SUN H Y , et al. Unsupervised domain adaptation through dynamically aligning both the feature and label spaces. IEEE Transactions on Circuits and Systems for Video Technology, 2022, 32 (12): 8562- 8573. doi: 10.1109/TCSVT.2022.3192135
2	TIAN Q , SUN H Y , MA C , et al. Heterogeneous domain adaptation with structure and classification space alignment. IEEE Transactions on Cybernetics, 2022, 52 (10): 10328- 10338. doi: 10.1109/TCYB.2021.3070545
3	TZENG E, HOFFMAN J, DARRELL T, et al. Simultaneous deep transfer across domains and tasks[C]//Proceedings of the IEEE International Conference on Computer Vision (ICCV). Santiago, Chile: IEEE Press, 2015: 4068-4076.
4	KONIUSZ P, TAS Y, PORIKLI F. Domain adaptation by mixture of alignments of second- or higher-order scatter tensors[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, USA: IEEE Press, 2017: 7139-7148.
5	TZENG E, HOFFMAN J, SAENKO K, et al. Adversarial discriminative domain adaptation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, USA: IEEE Press, 2017: 2962-2971.
6	SHEN J, QU Y R, ZHANG W N, et al. Wasserstein distance guided representation learning for domain adaptation[C]//Proceedings of the AAAI Conference on Artificial Intelligence. New Orleans, USA: AAAI, 2018: 4058-4069.
7	GANIN Y, LEMPITSKY V. Unsupervised domain adaptation by backpropagation[C]//Proceedings of International Conference on Machine Learning. [S. l.]: PMLR, 2015: 1180-1189.
8	SAITO K, WATANABE K, USHIKU Y, et al. Maximum classifier discrepancy for unsupervised domain adaptation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Salt Lake City, USA: IEEE Press, 2018: 3723-3732.
9	LIU H, CAO Z J, LONG M S, et al. Separate to adapt: open set domain adaptation via progressive separation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, USA: IEEE Press, 2019: 2922-2931.
10	ZHUANG J, CHEN Z, WEI P, et al. Open set domain adaptation by novel class discovery[EB/OL]. [2024-01-02]. https://arxiv.org/pdf/2203.03329.
11	LI G R, KANG G L, ZHU Y, et al. Domain consensus clustering for universal domain adaptation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Nashville, USA: IEEE Press, 2021: 9752-9761.
12	ZHENG X, HUANG Y, TANG J. Reliable cluster-based framework for open set domain adaptation[C]//Proceedings of the 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Rhodes Island, Greece: IEEE Press, 2023: 1-5.
13	FU B, CAO Z J, LONG M S, et al. Learning to detect open classes for universal domain adaptation[C]//Proceedings of ECCV 2020. Berlin, Germany: Springer, 2020: 567-583.
14	SAITO K, SAENKO K. OVANet: one-vs-all network for universal domain adaptation[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). Montreal, Canada: IEEE Press, 2021: 8980-8989.
15	CHANG W L, WANG H P, PENG W H, et al. All about structure: adapting structural information across domains for boosting semantic segmentation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, USA: IEEE Press, 2019: 1900-1909.
16	GONG B Q, SHI Y, SHA F, et al. Geodesic flow kernel for unsupervised domain adaptation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Providence, USA: IEEE Press, 2012: 2066-2073.
17	GUO Y, XIAO M. Cross language text classification via subspace co-regularized multi-view learning[EB/OL]. [2024-01-02]. https://arxiv.org/abs/1206.6481.
18	YAO T, PAN Y W, NGO C W, et al. Semi-supervised domain adaptation with subspace learning for visual recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston, USA: IEEE Press, 2015: 2142-2150.
19	QI F, YANG X S, XU C S. A unified framework for multimodal domain adaptation[C]//Proceedings of the 26th ACM International Conference on Multimedia. New York, USA: ACM, 2018: 429-437.
20	LONG M , ZHU H , WANG J , et al. Unsupervised domain adaptation with residual transfer networks. Advances in Neural Information Processing Systems, 2016, 29, 136- 144.
21	FRENCH G, MACKIEWICZ M, FISHER M. Self-ensembling for visual domain adaptation[EB/OL]. [2024-01-02]. https://arxiv.org/abs/1706.05208.
22	XU T, CHEN W, WANG P, et al. CDTRANS: cross-domain transformer for unsupervised domain adaptation[EB/OL]. [2024-01-02]. https://arxiv.org/abs/2109.06165.
23	DHAINI M , BERAR M , HONEINE P , et al. Unsupervised domain adaptation for regression using dictionary learning. Knowledge-Based Systems, 2023, 267, 110439. doi: 10.1016/j.knosys.2023.110439
24	BUSTO P P, GALL J. Open set domain adaptation[C]//Proceedings of the IEEE International Conference on Computer Vision (ICCV). Venice, Italy: IEEE Press, 2017: 754-763.
25	SAITO K, YAMAMOTO S, USHIKU Y, et al. Open set domain adaptation by backpropagation[C]//Proceedings of ECCV 2018. Berlin, Germany: Springer, 2018: 156-171.
26	BUCCI S, LOGHMANI M R, TOMMASI T. On the effectiveness of image rotation for open set domain adaptation[C]//Proceedings of ECCV 2020. Berlin, Germany: Springer, 2020: 422-438.
27	FENG Q Y, KANG G L, FAN H H, et al. Attract or distract: exploit the margin of open set[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). Seoul, Korea: IEEE Press, 2019: 7989-7998.
28	LI J , YANG L , WANG Q L , et al. WDAN: a weighted discriminative adversarial network with dual classifiers for fine-grained open-set domain adaptation. IEEE Transactions on Circuits and Systems for Video Technology, 2023, 33 (9): 5133- 5147. doi: 10.1109/TCSVT.2023.3249200
29	GRANDVALET Y , BENGIO Y . Semi-supervised learning by entropy minimization. Advances in Neural Information Processing Systems, 2004, 17, 529- 536.
30	SAENKO K, KULIS B, FRITZ M, et al. Adapting visual category models to new domains[C]//Proceedings of ECCV 2010. Berlin, Germany: Springer, 2010: 213-226.
31	VENKATESWARA H, EUSEBIO J, CHAKRABORTY S, et al. Deep hashing network for unsupervised domain adaptation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, USA: IEEE Press, 2017: 5385-5394.
32	PENG X C, USMAN B, KAUSHIK N, et al. VisDA: a synthetic-to-real benchmark for visual domain adaptation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Salt Lake City, USA: IEEE Press, 2018: 2021-2026.
33	LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft COCO: common objects in context[C]//Proceedings of ECCV 2014. Berlin, Germany: Springer, 2014: 740-755.
34	DENG J, DONG W, SOCHER R, et al. ImageNet: a large-scale hierarchical image database[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Miami, USA: IEEE Press, 2009: 248-255.
35	HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, USA: IEEE Press, 2016: 770-778.
36	SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[EB/OL]. [2024-01-02]. https://arxiv.org/abs/1409.1556.
37	LOSHCHILOV I, HUTTER F. SGDR: stochastic gradient descent with warm restarts[EB/OL]. [2024-01-02]. https://arxiv.org/abs/1608.03983v3.
38	GANIN Y , USTINOVA E , AJAKAN H , et al. Domain-adversarial training of neural networks. Journal of Machine Learning Research, 2016, 17 (59): 1- 35.
39	WANG Q, MENG F, BRECKON T. Progressively select and reject pseudo-labelled samples for open-set domain adaptation[EB/OL]. [2024-01-02]. https://arxiv.org/pdf/2110.12635.
40	SAITO K , KIM D , SCLAROFF S , et al. Universal domain adaptation through self supervision. Advances in Neural Information Processing Systems, 2020, 33, 16282- 16292.
41	JANG J H , NA B , SHIN D H , et al. Unknown-aware domain adversarial learning for open-set domain adaptation. Advances in Neural Information Processing Systems, 2022, 35, 16755- 16767.
42	LI W Y, LIU J, HAN B, et al. Adjustment and alignment for unbiased open set domain adaptation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver, Canada: IEEE Press, 2023: 24110-24119.
43	LIU Z F , CHEN G , LI Z J , et al. PSDC: a prototype-based shared-dummy classifier model for open-set domain adaptation. IEEE Transactions on Cybernetics, 2023, 53 (11): 7353- 7366. doi: 10.1109/TCYB.2022.3228301
44	LUO Y, WANG Z, HUANG Z, et al. Progressive graph learning for open-set domain adaptation[C]//Proceedings of International Conference on Machine Learning. [S. l.]: PMLR, 2020: 6468-6478.
45	XU Y , CHEN L , DUAN L , et al. Open set domain adaptation with soft unknown-class rejection. IEEE Transactions on Neural Networks and Learning Systems, 2023, 34 (3): 1601- 1612. doi: 10.1109/TNNLS.2021.3105614
46	CHANG D L , SAIN A , MA Z Y , et al. Mind the gap: open set domain adaptation via mutual-to-separate framework. IEEE Transactions on Circuits and Systems for Video Technology, 2024, 34 (6): 4159- 4174. doi: 10.1109/TCSVT.2023.3326862
47	MAATEN L , HINTON G . Visualizing data using t-SNE. Journal of Machine Learning Research, 2008, 9 (11): 2579- 2605.

[1]	安畅, 毛力. 一种基于迁移学习的双代理辅助船型优化方法[J]. 计算机工程, 2025, 51(9): 317-327.
[2]	逯暄, 景路琪, 彭甫镕. 基于增量学习的结直肠息肉分割方法[J]. 计算机工程, 2025, 51(7): 284-293.
[3]	欧阳昱中, 韩锐, 刘驰. 边缘侧领域自适应中长尾视觉识别技术研究[J]. 计算机工程, 2025, 51(7): 171-179.
[4]	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.
[5]	张欢, 王晨, 单景东, 仇润鹤. 基于领域自适应与注意力机制的电梯安全风险预测[J]. 计算机工程, 2025, 51(2): 86-93.
[6]	易鹏, 杨晔, 严仕嘉. 基于MPCNN模型的sEMG快速迁移学习的手势识别应用研究[J]. 计算机工程, 2025, 51(1): 304-311.
[7]	李致金, 汤佳辉, 闫金凤. 基于边缘计算的轻量化识别方法[J]. 计算机工程, 2024, 50(6): 287-295.
[8]	马晓月, 陈媛媛. 基于对抗学习和引导机制的视盘和视杯联合分割[J]. 计算机工程, 2024, 50(12): 59-69.
[9]	包善书, 车波, 邓林红. 基于双源域迁移学习的肺音信号识别[J]. 计算机工程, 2023, 49(9): 295-302, 312.
[10]	王爱玲, 马文臻, 邹自明, 钟佳. 基于领域自适应的卫星工程参数异常检测[J]. 计算机工程, 2023, 49(5): 29-37,47.
[11]	白俊卿, 韩柏迅, 张丰侠. 基于深度学习的无人机图像语义分割算法研究[J]. 计算机工程, 2023, 49(4): 233-239.
[12]	罗少聪, 张旭东, 万乐, 谢林芳, 黎书玉. 结合图像特征迁移的光场深度估计方法[J]. 计算机工程, 2023, 49(4): 206-216.
[13]	郑云涛, 叶家炜. 基于茫然传输协议的FATE联邦迁移学习方案[J]. 计算机工程, 2023, 49(2): 24-30.
[14]	伍洲, 杨寒石, 邬俊俊, 张海军, 宋晴. 进化迁移优化算法综述[J]. 计算机工程, 2023, 49(1): 1-14.
[15]	邱鸿辉, 刘海林, 陈磊. 基于协方差矩阵调整的多目标多任务优化算法[J]. 计算机工程, 2022, 48(8): 306-312.

选择文件类型/文献管理软件名称

选择包含的内容

基于过渡桥接机制的对抗性开放集领域自适应

Adversarial Open-Set Domain Adaptation via Transition Bridge Mechanism

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 47

相关文章 15

编辑推荐

Metrics

本文评价

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

基于过渡桥接机制的对抗性开放集领域自适应

Adversarial Open-Set Domain Adaptation via Transition Bridge Mechanism

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 47

相关文章 15

编辑推荐

Metrics

本文评价