paper-with-me

Papers

Disentangling by Factorising

2018-02-16 · ICML 2018 7 · Hyunjik Kim, andriy mnih

We define and address the problem of unsupervised learning of disentangled representations on data generated from independent factors of variation. We propose FactorVAE, a method that disentangles by encouraging the distribution of representations to be factorial and hence independent across the dimensions. We show that it improves upon $\beta$-VAE by providing a better trade-off between disentanglement and reconstruction quality. Moreover, we highlight the problems of a commonly used disentanglement metric and introduce a new metric that does not suffer from them.

📄 PDF Abstract BibTeX arXiv:1802.05983

Code (17)

1Konny/FactorVAE pytorch
AliLotfi92/Disentangling-by-Factorising pytorch
AliLotfi92/Disentangling_by_Factorising pytorch
Guiliang/FactorVAE pytorch
Michedev/FactorVAE pytorch
OZA15015/custom_FVAE pytorch
carbonati/variational-zoo tf
clementchadebec/benchmark_VAE pytorch
danielbraithwt/Readings
ducnx/FactorVAE pytorch
elda27/FactorVAE tf
facebookresearch/disentangling-correlated-factors pytorch
gene-chou/conditional-factor-vae pytorch
mcharrak/discreteVAE tf
mmrl/disent-and-gen pytorch
nicolasigor/FactorVAE tf
wangdedi1997/Disentanglement-Beta-FactorVAE tf

Tasks

Disentanglement

Similar Papers 제목 키워드 기반

Factorising AMR generation through syntax

2018-04-20 · NAACL 2019 6 · Kris Cao, Stephen Clark

Generating from Abstract Meaning Representation (AMR) is an underspecified problem, as many syntactic decisions are not constrained by the semantic graph. To explicitly account for this underspecification, we break down …

Abstract Meaning Representation

Deep Learning for Audio Transcription on Low-Resource Datasets

2018-07-10 · Veronica Morfi, Dan Stowell

In training a deep learning system to perform audio transcription, two practical problems may arise. Firstly, most datasets are weakly labelled, having only a list of events present in each recording without any temporal…

Deep Learning

Factorising Meaning and Form for Intent-Preserving Paraphrasing

2021-05-31 · ACL 2021 5 · Tom Hosking, Mirella Lapata

We propose a method for generating paraphrases of English questions that retain the original intent but use a different surface form. Our model combines a careful choice of training objective with a principled informatio…

DecoderFormParaphrase GenerationParaphrase Identification

Successes and Limitations of Object-centric Models at Compositional Generalisation

2024-12-25 · Milton L. Montero, Jeffrey S. Bowers, Gaurav Malhotra

In recent years, it has been shown empirically that standard disentangled latent variable models do not support robust compositional learning in the visual domain. Indeed, in spite of being designed with the goal of fact…

Learning Disentangling and Fusing Networks for Face Completion Under Structured Occlusions

2017-12-13 · Zhihang Li, Yibo Hu, Ran He

Face completion aims to generate semantically new pixels for missing facial components. It is a challenging generative task due to large variations of face appearance. This paper studies generative face completion under …

DecoderFacial InpaintingGenerative Adversarial Network