paper-with-me

홈 › Papers

Disentangled VAE Representations for Multi-Aspect and Missing Data

2018-06-24 · Samuel K. Ainsworth, Nicholas J. Foti, Emily B. Fox

Many problems in machine learning and related application areas are fundamentally variants of conditional modeling and sampling across multi-aspect data, either multi-view, multi-modal, or simply multi-group. For example, sampling from the distribution of English sentences conditioned on a given French sentence or sampling audio waveforms conditioned on a given piece of text. Central to many of these problems is the issue of missing data: we can observe many English, French, or German sentences individually but only occasionally do we have data for a sentence pair. Motivated by these applications and inspired by recent progress in variational autoencoders for grouped data, we develop factVAE, a deep generative model capable of handling multi-aspect data, robust to missing observations, and with a prior that encourages disentanglement between the groups and the latent dimensions. The effectiveness of factVAE is demonstrated on a variety of rich real-world datasets, including motion capture poses and pictures of faces captured from varying poses and perspectives.

📄 PDF Abstract BibTeX arXiv:1806.09060

Code (0)

등록된 구현이 없습니다.

Tasks

DisentanglementSentence

Similar Papers 제목 키워드 기반

Learning Disentangled Representations of Texts with Application to Biomedical Abstracts

2018-04-19 · EMNLP 2018 10 · Sarthak Jain, Edward Banner, Jan-Willem van de Meent, Iain J. Marshall 외

We propose a method for learning disentangled representations of texts that code for distinct and complementary aspects, with the aim of affording efficient model transfer and interpretability. To induce disentangled emb…

Retrieval

Learning Disentangled Representations of Video with Missing Data

2020-06-23 · Armand Comas-Massagué, Chi Zhang, Zlatan Feric, Octavia Camps 외

Missing data poses significant challenges while learning representations of video sequences. We present Disentangled Imputed Video autoEncoder (DIVE), a deep generative model that imputes and predicts future video frames…

Learning Disentangled Representations of Videos with Missing Data

2020-12-01 · NeurIPS 2020 12 · Armand Comas, Chi Zhang, Zlatan Feric, Octavia Camps 외

Missing data poses significant challenges while learning representations of video sequences. We present Disentangled Imputed Video autoEncoder (DIVE), a deep generative model that imputes and predicts future video frames…

Object

Aspect-based Sentiment Analysis using BERT with Disentangled Attention

2021-07-18 · ICML 2021 - LXAI Workshop 2021 7 · Emanuel H. Silva, Ricardo M. Marcacini

Aspect-Based Sentiment Analysis (ABSA) tasks aim to identify consumers' opinions about different aspects of products or services. BERT-based language models have been used successfully in applications that require a deep…

Aspect-Based Sentiment AnalysisAspect-Based Sentiment Analysis (ABSA)Representation LearningSentiment Analysis

OmniPrism: Learning Disentangled Visual Concept for Image Generation

2024-12-16 · Yangyang Li, Daqing Liu, Wu Liu, Allen He 외

Creative visual concept generation often draws inspiration from specific concepts in a reference image to produce relevant outcomes. However, existing methods are typically constrained to single-aspect concept generation…

DisentanglementImage Generation