Related references
Note: Only part of the references are listed.
Article
Computer Science, Artificial Intelligence
Yiju Yang et al.
Summary: This paper proposes a dual-module network architecture that encourages the learning of domain invariant features. The architecture is applicable to any model that uses domain invariant features for unsupervised domain adaptation. Through adversarial training and discrepancy loss, the two modules learn more domain invariant and domain discriminative features respectively. Experimental results show that the proposed approach outperforms state-of-the-art methods in unsupervised domain adaptation tasks.
Article
Computer Science, Artificial Intelligence
Adu Asare Baffour et al.
Summary: This paper presents a Generic Domain Adaptation Network (GDAN) to address the limitations of prior self-supervised methods in domain adaptation. GDAN selects appropriate pretext tasks and utilizes semantic neighbor cluster to align the features of the two domains. It also introduces a weighted target loss function to accommodate partially labeled target data. Experimental results demonstrate the effectiveness of GDAN on four benchmark datasets.
Article
Computer Science, Artificial Intelligence
Rakesh Kumar Sanodiya et al.
Summary: In supervised learning, domain adaptation aims to address the issue of different data distributions in different domains by learning manifold features and formulating a strong objective function to reduce divergence between domains. The newly proposed MEJGSA method shows significant improvements over existing domain adaptation methods in experiments.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Hui Tang et al.
Summary: Unsupervised domain adaptation tackles the issue of classifying data in an unlabeled target domain while having labeled source domain data. This paper introduces a novel method called DisClusterDA, which formulates the domain adaptation problem as discriminative clustering and utilizes source data for joint training. Experimental results demonstrate that DisClusterDA outperforms existing methods on several benchmark datasets.
PATTERN RECOGNITION
(2022)
Article
Environmental Sciences
Mohamad Dhaini et al.
Summary: This paper proposes a nonlinear method for blind unmixing using a deep convolutional autoencoder, which achieves endmembers estimation and abundance estimation. The performance of the proposed method is demonstrated to be better than existing methods through experiments on synthetic and real data.
Article
Computer Science, Artificial Intelligence
Chunmei He et al.
Summary: This paper investigates the problem of partial domain adaptation and proposes a manifold discrimination partial adversarial domain adaptation (MDPDA) method, which achieves effective domain adaptation by combining manifold learning and adversarial learning. Experimental results on several benchmark datasets demonstrate the superior performance of the proposed method compared to the state-of-the-art methods.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Christoph Raab et al.
Summary: Deep learning has achieved state-of-the-art performance in many applications, but its generalization capabilities are limited. Joint adversarial domain adaptation networks have been the preferred models for adapting from source to target domains. However, this study proposes a new network architecture called DATSA, which does not rely on pseudo labels for alignment and achieves domain adaptation through self-supervised learning. Experimental results demonstrate that DATSA is competitive in terms of both adaptation and accuracy.
Article
Computer Science, Artificial Intelligence
Mei Wang et al.
Article
Automation & Control Systems
Guannan Qu et al.
IEEE TRANSACTIONS ON AUTOMATIC CONTROL
(2020)
Article
Computer Science, Artificial Intelligence
Garrett Wilson et al.
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY
(2020)
Article
Computer Science, Artificial Intelligence
Ramin Nikzad-Langerodi et al.
KNOWLEDGE-BASED SYSTEMS
(2020)
Article
Computer Science, Artificial Intelligence
Olga Russakovsky et al.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2015)
Article
Computer Science, Artificial Intelligence
Makoto Yamada et al.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2014)
Article
Computer Science, Artificial Intelligence
Amaury Habrard et al.
INTERNATIONAL JOURNAL ON ARTIFICIAL INTELLIGENCE TOOLS
(2013)
Review
Physics, Multidisciplinary
Joao Carlos Alves Barata et al.
BRAZILIAN JOURNAL OF PHYSICS
(2012)
Article
Computer Science, Artificial Intelligence
Sinno Jialin Pan et al.
IEEE TRANSACTIONS ON NEURAL NETWORKS
(2011)
Article
Computer Science, Artificial Intelligence
Amir Beck et al.
SIAM JOURNAL ON IMAGING SCIENCES
(2009)
Article
Computer Science, Information Systems
Joel A. Tropp et al.
IEEE TRANSACTIONS ON INFORMATION THEORY
(2007)
Article
Computer Science, Artificial Intelligence
Xin Geng et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2007)
