Heterogeneous Domain Adaptation for Multiple Classes

By Joey Tianyi Zhou, Ivor Wai-Hung Tsang, Sinno Jialin Pan, Mingkui Tan. 2014

159 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Domain Adaptation for Visual Applications: A Comprehensive Survey (2017, background): “ns within the classes to be aligned while maintaining the structure of the data. It requires a limited amount of labeled target data for each class to be paired with the corresponding source classes. [10] proposes a sparse and class-invariant feature mapping that leverages the weight vectors of the ”
Hybrid Heterogeneous Transfer Learning through Deep Learning (2014, background): “Alternatively, one can learn an asymmetric transformation to map data from one domain to another domain (Kulis, Saenko, and Darrell 2011; Zhou et al. 2014).”
Transfer Neural Trees for Heterogeneous Domain Adaptation (2016, methodology): “DS → DT SVMt NNt MMDT [18] HFA [21] SHFR [19] SCP [23] TNT tag → image 63.”
Deep Visual Domain Adaptation: A Survey (2018, background): “[142] proposed a sparse and class-invariant feature transformation matrix to map the weight vector of classiﬁers learned from the source domain to the target domain.”
Transfer Learning for Molecular Cancer Classification Using Deep Neural Networks (2019, background): “Suchmolecular analyses typically have few samples with huge number of features; hence using feature selection algorithms becomes almost inevitable [2], [12], [14].”
Transfer Hashing with Privileged Information (2016, background): “…knowledge across different domains so that rich source domain knowlege can be used to build better classifiers on a target domain where the transferred knowledge can be labels [Zhou et al., 2014b], features [Pan et al., 2011], crossdomain correspondences [Zhou et al., 2014a; Zhou et al., 2016].”