Y Jang, H Lee, SJ Hwang… - … on machine learning, 2019 - proceedings.mlr.press
… use attention maps generated from featuremaps or Jacobians for transferring the source … Our goal is learning to learntransfer rules for performing knowledgetransfer in an automatic …
J Zhou, S Pan, I Tsang, Y Yan - Proceedings of the AAAI Conference on …, 2014 - ojs.aaai.org
… a deeplearning approach to learn a featuremapping … a deeplearning method to simultaneously learn a feature transfor… from lower-level features to higher-level features in the …
F Gao, H Yoon, T Wu, X Chu - Expert Systems with Applications, 2020 - Elsevier
… Featuretransfer aims to identify a joint featuremap shared by the source and target domains… domains have shared knowledge and representations, featurestransferred from the source …
C Tan, F Sun, T Kong, W Zhang, C Yang… - … Networks and Machine …, 2018 - Springer
… In contrast, traditional machinelearning methods need to design features manually that … Mapping-based deeptransferlearning refers to mapping instances from the source domain and …
… transferlearning is successful in learningfeatures relevant not only for nighttime light prediction but also for poverty mapping. … these features are highly informative for poverty mapping …
… to featurelearning for transferlearning are required. In this section, we first introduce a featurelearning approach to transferlearning … Another context is to learn a featuremapping to …
… The number of featuremaps, filter size, and size of the featuremaps are hyperparameters in … that one has to optimize for a learning task. A deep CNN architecture is multi-layered, with …
… Meanwhile, we introduce featuremap loss and map … featuremap loss produced by discriminator is beneficial for computing the discriminative regions from both real and generated …
M Long, Y Cao, J Wang… - … on machine learning, 2015 - proceedings.mlr.press
… The characteristic kernel associated with the featuremap φ, k (xs, xt) = <φ (xs) ,φ (xt)>, is … We compare the DAN model to state-of-the-art transferlearning and deeplearning methods on …