Drop to Adapt: Learning Discriminative Features for Unsupervised Domain Adaptation [ICCV2019] [PyTorch] Cluster Alignment with a Teacher for Unsupervised Domain Adaptation [ICCV2019] [Tensorflow] Unsupervised Domain Adaptation via Regularized Conditional Alignment [ICCV2019] Attending to Discriminative Certainty...
Domain-Invariant Adversarial Learning for Unsupervised Domain Adaption [arXiv 30 Nov 2018] Unsupervised Domain Adaptation using Deep Networks with Cross-Grafted Stacks [arXiv 17 Feb 2019] DART: Domain-Adversarial Residual-Transfer Networks for Unsupervised Cross-Domain Image Classification [arXiv 30 Dec...
Cluster Contrast for Unsupervised Person Re-Identification (CVPR 21) 动机:在现有Unsupervise的 reID的pipeline中,memory通常储存的是instance feature,但是更新instance feature会导致2个问题:1)GPU内存开销大;2)各个类的instance数量不一致,导致cluster更新不一致,具有少样本的cluster更新较快 方法:memory中储存cluster ...
Aggregat- ing randomized clustering-promoting invariant projections for domain adaptation. IEEE Trans. Pattern Anal. Mach. In- tell., 41(5):1027–1042, 2018. 2 [43] Jian Liang, Ran He, Zhenan Sun, and Tieniu Tan. Distant supervised centroid shift: A simple ...
1) This paper proposes a new deep transfer learning algorithm for one-class anomaly detection. Differently from current anomaly detection methods with transfer learning, this algorithm can realize the transition of one-class detection rule in the process of adaptively extracting domain-invariant feature...
Most UDA methods for pair-wise similarity matching have been proposed for image-based person ReID, and adopt approaches for domain-invariant feature learning [30, 16, 38, 24, 25, 27], adversarial training [44, 43, 34, 7, 2, 31], and cluster- ing [...
(Color online) Operating mechanism of the domain generalization methods based on sample cluster. (a) Triplet loss; (b) center loss. 对比学习也被常用于开发样本集群方法. 2022年, Ragab等人[68]提出了一种条件对比域泛化故障诊断方法, 它通过将所有域中相同类样本的互信息最大化, 而不同类样本的互信息...
explanatory relation, that is, how dependent the inferences that the explanation enables are on non-included situations. My argument is that explanations of a homeostatic property cluster fall on a continuum of explanatory power or goodness described by the domain of applicability and the contrastive-...
Learning to cluster in order to transfer across domains and tasks [ICLR2018] [Bolg] [Pytorch] Self-Ensembling for Visual Domain Adaptation [ICLR2018] Minimal-Entropy Correlation Alignment for Unsupervised Deep Domain Adaptation [ICLR2018] [TensorFlow] Associative Domain Adaptation [ICCV2017] [TensorFlow...
Learning to cluster in order to transfer across domains and tasks [ICLR2018] [Bolg] [Pytorch] Self-Ensembling for Visual Domain Adaptation [ICLR2018] Minimal-Entropy Correlation Alignment for Unsupervised Deep Domain Adaptation [ICLR2018] [TensorFlow] Associative Domain Adaptation [ICCV2017] [TensorFlow...