Cross-Domain Latent Modulation for Variational Transfer Learning
We propose a cross-domain latent modulation mechanism within a variational autoencoders (VAE) framework to enable improved transfer learning. Our key idea is to procure deep representations from one data domain and use it as perturbation to the reparameterization of the latent variable in another domain. Specifically, deep representations of the source and target domains are first extracted by a unified inference model and aligned by employing gradient reversal. Second, the learned deep representations are cross-modulated to the latent encoding of the alternate domain. The consistency between the reconstruction from the modulated latent encoding and the generation using deep representation samples is then enforced in order to produce inter-class alignment in the latent space. We apply the proposed model to a number of transfer learning tasks including unsupervised domain adaptation and image-toimage translation. Experimental results show that our model gives competitive performance.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain AdaptationTransfer LearningTranslationUnsupervised Domain AdaptationSimilar Papers 제목 키워드 기반
Variational Transfer Learning using Cross-Domain Latent Modulation
To successfully apply trained neural network models to new domains, powerful transfer learning solutions are essential. We propose to introduce a novel cross-domain latent modulation mechanism to a variational autoencode…
Domain AdaptationImage-to-Image TranslationTransfer LearningUnsupervised Domain AdaptationDeep Variational Transfer: Transfer Learning through Semi-supervised Deep Generative Models
In real-world applications, it is often expensive and time-consuming to obtain labeled examples. In such cases, knowledge transfer from related domains, where labels are abundant, could greatly reduce the need for extens…
General ClassificationTransfer LearningLatent Domain Transfer: Crossing modalities with Bridging Autoencoders
Domain transfer is a exciting and challenging branch of machine learning because models must learn to smoothly transfer between domains, preserving local variations and capturing many aspects of variation without labels.…
Generative Adversarial NetworkA Variational Bayesian Approach to Learning Latent Variables for Acoustic Knowledge Transfer
We propose a variational Bayesian (VB) approach to learning distributions of latent variables in deep neural network (DNN) models for cross-domain knowledge transfer, to address acoustic mismatches between training and t…
Acoustic Scene ClassificationScene ClassificationTransfer LearningMetaModulation: Learning Variational Feature Hierarchies for Few-Shot Learning with Fewer Tasks
Meta-learning algorithms are able to learn a new task using previously learned knowledge, but they often require a large number of meta-training tasks which may not be readily available. To address this issue, we propose…
DiversityFew-Shot LearningMeta-Learning