TY - JOUR
T1 - Deep Label Propagation with Nuclear Norm Maximization for Visual Domain Adaptation
AU - Wang, Wei
AU - Li, Hanyang
AU - Wang, Cong
AU - Huang, Chao
AU - Ding, Zhengming
AU - Nie, Feiping
AU - Cao, Xiaochun
N1 - Publisher Copyright:
© 1992-2012 IEEE.
PY - 2025
Y1 - 2025
N2 - Domain adaptation aims to leverage abundant label information from a source domain to an unlabeled target domain with two different distributions. Existing methods usually rely on a classifier to generate high-quality pseudo-labels for the target domain, facilitating the learning of discriminative features. Label propagation (LP), as an effective classifier, propagates labels from the source domain to the target domain by designing a smooth function over a similarity graph, which represents structural relationships among data points in feature space. However, LP has not been thoroughly explored in deep neural network-based domain adaptation approaches. Additionally, the probability labels generated by LP are low-confident and LP is sensitive to class imbalance problem. To address these problems, we propose a novel approach for domain adaptation named deep label propagation with nuclear norm maximization (DLP-NNM). Specifically, we employ the constraint of nuclear norm maximization to enhance both label confidence and class diversity in LP and propose an efficient algorithm to solve the corresponding optimization problem. Subsequently, we utilize the proposed LP to guide the classifier layer in a deep discriminative adaptation network using the cross-entropy loss. As such, the network could produce more reliable predictions for the target domain, thereby facilitating more effective discriminative feature learning. Extensive experimental results on three cross-domain benchmark datasets demonstrate that the proposed DLP-NNM surpasses existing state-of-the-art domain adaptation approaches.
AB - Domain adaptation aims to leverage abundant label information from a source domain to an unlabeled target domain with two different distributions. Existing methods usually rely on a classifier to generate high-quality pseudo-labels for the target domain, facilitating the learning of discriminative features. Label propagation (LP), as an effective classifier, propagates labels from the source domain to the target domain by designing a smooth function over a similarity graph, which represents structural relationships among data points in feature space. However, LP has not been thoroughly explored in deep neural network-based domain adaptation approaches. Additionally, the probability labels generated by LP are low-confident and LP is sensitive to class imbalance problem. To address these problems, we propose a novel approach for domain adaptation named deep label propagation with nuclear norm maximization (DLP-NNM). Specifically, we employ the constraint of nuclear norm maximization to enhance both label confidence and class diversity in LP and propose an efficient algorithm to solve the corresponding optimization problem. Subsequently, we utilize the proposed LP to guide the classifier layer in a deep discriminative adaptation network using the cross-entropy loss. As such, the network could produce more reliable predictions for the target domain, thereby facilitating more effective discriminative feature learning. Extensive experimental results on three cross-domain benchmark datasets demonstrate that the proposed DLP-NNM surpasses existing state-of-the-art domain adaptation approaches.
KW - deep label propagation
KW - discriminative feature learning
KW - Domain adaptation
KW - nuclear norm maximization
UR - http://www.scopus.com/inward/record.url?scp=85216847052&partnerID=8YFLogxK
U2 - 10.1109/TIP.2025.3533199
DO - 10.1109/TIP.2025.3533199
M3 - 文章
AN - SCOPUS:85216847052
SN - 1057-7149
JO - IEEE Transactions on Image Processing
JF - IEEE Transactions on Image Processing
ER -