Corpus ID: 236447473

Nearest Neighborhood-Based Deep Clustering for Source Data-absent Unsupervised Domain Adaptation

  title={Nearest Neighborhood-Based Deep Clustering for Source Data-absent Unsupervised Domain Adaptation},
  author={Song Tang and Yan Yang and Zhiyuan Ma and Norman Hendrich and Fanyu Zeng and Shuzhi Sam Ge and Changshui Zhang and Jianwei Zhang},
In the classic setting of unsupervised domain adaptation (UDA), the labeled source data are available in the training phase. However, in many real-world scenarios, owing to some reasons such as privacy protection and information security, the source data is inaccessible, and only a model trained on the source domain is available. This paper proposes a novel deep clustering method for this challenging task. Aiming at the dynamical clustering at feature-level, we introduce extra constraints… Expand


Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering
  • Hui Tang, Ke Chen, K. Jia
  • Computer Science
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2020
This work describes the proposed method as Structurally Regularized Deep Clustering (SRDC), where it enhances target discrimination with clustering of intermediate network features, and enhance structural regularization with soft selection of less divergent source examples. Expand
Model Adaptation: Unsupervised Domain Adaptation Without Source Data
This paper proposes a new framework, which is referred to as collaborative class conditional generative adversarial net, to bypass the dependence on the source data and achieves superior performance on multiple adaptation tasks with only unlabeled target data, which verifies its effectiveness in this challenging setting. Expand
Distant Supervised Centroid Shift: A Simple and Efficient Approach to Visual Domain Adaptation
This paper design a unified objective without accessing the source domain data and adopt an alternating minimization scheme to iteratively discover the pseudo target labels, invariant subspace, and target centroids, which could be regarded as a well-performing baseline for domain adaptation tasks. Expand
Domain Adaptation without Source Data
This work introduces source data-free domain adaptation (SFDA), to leverage a pre-trained model from the source domain and progressively update the target model in a self-learning manner, observing that target samples with lower self-entropy measured by the pre- trained source model are more likely to be classified correctly. Expand
Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation
This work proposes a simple yet generic representation learning framework, named SHOT, which freezes the classifier module (hypothesis) of the source model and learns the target-specific feature extraction module by exploiting both information maximization and self-supervised pseudo-labeling to implicitly align representations from the target domains to the source hypothesis. Expand
Cluster Alignment With a Teacher for Unsupervised Domain Adaptation
Cluster Alignment with a Teacher (CAT) is proposed for unsupervised domain adaptation, which can effectively incorporate the discriminative clustering structures in both domains for better adaptation. Expand
Domain-Symmetric Networks for Adversarial Domain Adaptation
This paper proposes a new domain adaptation method called Domain-Symmetric Networks (SymNets), which is based on a symmetric design of source and target task classifiers, based on which an additional classifier is constructed that shares with them its layer neurons. Expand
Beyond the shortest path: Unsupervised domain adaptation by Sampling Subspaces along the Spline Flow
A novel concept is proposed that allows to explicitly integrate multi-source domains while the previous one uses the mean of all sources, which enables to model better the domain shift and take fully advantage of the training datasets. Expand
Deep Hashing Network for Unsupervised Domain Adaptation
This is the first research effort to exploit the feature learning capabilities of deep neural networks to learn representative hash codes to address the domain adaptation problem and proposes a novel deep learning framework that can exploit labeled source data and unlabeled target data to learn informative hash codes, to accurately classify unseen target data. Expand
Part-aware Progressive Unsupervised Domain Adaptation for Person Re-Identification
  • Fan Yang, Ke Yan, +6 authors W. Gao
  • Computer Science
  • IEEE Transactions on Multimedia
  • 2021
An innovative part-aware progressive adaptation network (PPAN) that exploits global and local relations for UDA-based ReID across domains and a novel progressive adaptation strategy (PAS) is designed that effectively alleviates the negative influence of outlier source identities. Expand