An Improved Semi-Supervised VAE for Learning Disentangled Representations

2020-06-12 · Weili Nie, Zichao Wang, Ankit B. Patel, Richard G. Baraniuk

Learning interpretable and disentangled representations is a crucial yet challenging task in representation learning. In this work, we focus on semi-supervised disentanglement learning and extend work by Locatello et al. (2019) by introducing another source of supervision that we denote as label replacement. Specifically, during training, we replace the inferred representation associated with a data point with its ground-truth representation whenever it is available. Our extension is theoretically inspired by our proposed general framework of semi-supervised disentanglement learning in the context of VAEs which naturally motivates the supervised terms commonly used in existing semi-supervised VAEs (but not for disentanglement learning). Extensive experiments on synthetic and real datasets demonstrate both quantitatively and qualitatively the ability of our extension to significantly and consistently improve disentanglement with very limited supervision.

📄 PDF Abstract BibTeX arXiv:2006.07460

Code (0)

등록된 구현이 없습니다.

Tasks

Disentanglement Representation Learning

Semi-Supervised Learning by Disentangling and Self-Ensembling Over Stochastic Latent Space

2019-07-22 · Prashnna Kumar Gyawali, Zhiyuan Li, Sandesh Ghimire, Linwei Wang

The success of deep learning in medical imaging is mostly achieved at the cost of a large labeled data set. Semi-supervised learning (SSL) provides a promising solution by leveraging the structure of unlabeled data to im…

Data Augmentation Multi-Label Classification MUlTI-LABEL-ClASSIFICATION Representation Learning

Boosting Multi-Speaker Expressive Speech Synthesis with Semi-supervised Contrastive Learning

2023-10-26 · Xinfa Zhu, Yuke Li, Yi Lei, Ning Jiang 외

This paper aims to build a multi-speaker expressive TTS system, synthesizing a target speaker's speech with multiple styles and emotions. To this end, we propose a novel contrastive learning-based TTS approach to transfe…

Contrastive Learning Expressive Speech Synthesis Speech Synthesis

DisenSemi: Semi-supervised Graph Classification via Disentangled Representation Learning

2024-07-19 · Yifan Wang, Xiao Luo, Chong Chen, Xian-Sheng Hua 외

Graph classification is a critical task in numerous multimedia applications, where graphs are employed to represent diverse types of multimedia data, including images, videos, and social networks. Nevertheless, in real-w…

Classification Graph Classification Representation Learning

Learning Disentangled Representations with Semi-Supervised Deep Generative Models

2017-06-01 · NeurIPS 2017 12 · N. Siddharth, Brooks Paige, Jan-Willem van de Meent, Alban Desmaison 외

Variational autoencoders (VAEs) learn representations of data by jointly training a probabilistic encoder and decoder network. Typically these models encode all features of the data into a single variable. Here we are in…

Decoder Representation Learning

Semi-Supervised StyleGAN for Disentanglement Learning

2020-03-06 · ICML 2020 1 · Weili Nie, Tero Karras, Animesh Garg, Shoubhik Debnath 외

Disentanglement learning is crucial for obtaining disentangled representations and controllable generation. Current disentanglement methods face several inherent limitations: difficulty with high-resolution images, prima…