paper-with-me

홈 › Papers

Cross-Domain Latent Modulation for Variational Transfer Learning

2020-12-21 · Jinyong Hou, Jeremiah D. Deng, Stephen Cranefield, Xuejie Ding

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.

📄 PDF Abstract BibTeX arXiv:2012.11727

Code (0)

등록된 구현이 없습니다.

Tasks

Domain AdaptationTransfer LearningTranslationUnsupervised Domain Adaptation

Similar Papers 제목 키워드 기반

Variational Transfer Learning using Cross-Domain Latent Modulation

2022-05-31 · Jinyong Hou, Jeremiah D. Deng, Stephen Cranefield, Xuejie Din

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 Adaptation

Deep Variational Transfer: Transfer Learning through Semi-supervised Deep Generative Models

2018-12-07 · Marouan Belhaj, Pavlos Protopapas, Weiwei Pan

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 Learning

Latent Domain Transfer: Crossing modalities with Bridging Autoencoders

2019-05-01 · ICLR 2019 5 · Yingtao Tian, Jesse Engel

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 Network

A Variational Bayesian Approach to Learning Latent Variables for Acoustic Knowledge Transfer

2021-10-16 · Hu Hu, Sabato Marco Siniscalchi, Chao-Han Huck Yang, Chin-Hui Lee

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 Learning

MetaModulation: Learning Variational Feature Hierarchies for Few-Shot Learning with Fewer Tasks

2023-05-17 · Wenfang Sun, Yingjun Du, XianTong Zhen, Fan Wang 외

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