paper-with-me

홈 › Papers

Latent Space Factorisation and Manipulation via Matrix Subspace Projection

2019-07-26 · ICML 2020 1 · Xiao Li, Chenghua Lin, Ruizhe Li, Chaozheng Wang, Frank Guerin

We tackle the problem disentangling the latent space of an autoencoder in order to separate labelled attribute information from other characteristic information. This then allows us to change selected attributes while preserving other information. Our method, matrix subspace projection, is much simpler than previous approaches to latent space factorisation, for example not requiring multiple discriminators or a careful weighting among their loss functions. Furthermore our new model can be applied to autoencoders as a plugin, and works across diverse domains such as images or text. We demonstrate the utility of our method for attribute manipulation in autoencoders trained across varied domains, using both human evaluation and automated methods. The quality of generation of our new model (e.g. reconstruction, conditional generation) is highly competitive to a number of strong baselines.

📄 PDF Abstract BibTeX arXiv:1907.12385

Code (2)

lissomx/MSP 공식 구현 pytorch
elhamod/phylonn pytorch

Tasks

AttributeFace GenerationFace SwappingImage Generation

Methods 이 논문이 사용한 방법론

Solana Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

Subspace Change-Point Detection via Low-Rank Matrix Factorisation

2021-10-08 · Euan Thomas McGonigle, Hankui Peng

Multivariate time series can often have a large number of dimensions, whether it is due to the vast amount of collected features or due to how the data sources are processed. Frequently, the main structure of the high-di…

Change Point DetectionTime SeriesTime Series Analysis

A Variational Autoencoder for Probabilistic Non-Negative Matrix Factorisation

2019-06-13 · ICLR 2019 5 · Steven Squires, Adam Prügel Bennett, Mahesan Niranjan

We introduce and demonstrate the variational autoencoder (VAE) for probabilistic non-negative matrix factorisation (PAE-NMF). We design a network which can perform non-negative matrix factorisation (NMF) and add in aspec…

Time SeriesTime Series Analysis

Linear Shape Deformation Models with Local Support Using Graph-based Structured Matrix Factorisation

2015-10-28 · CVPR 2016 6 · Florian Bernard, Peter Gemmar, Frank Hertel, Jorge Goncalves 외

Representing 3D shape deformations by linear models in high-dimensional space has many applications in computer vision and medical imaging, such as shape-based interpolation or segmentation. Commonly, using Principal Com…

Synthesizing Human Faces using Latent Space Factorization and Local Weights (Extended Version)

2021-07-19 · Minyoung Kim, Young J. Kim

We propose a 3D face generative model with local weights to increase the model's variations and expressiveness. The proposed model allows partial manipulation of the face while still learning the whole face mesh. For thi…

Online Identification and Tracking of Subspaces from Highly Incomplete Information

2010-06-21 · Laura Balzano, Robert Nowak, Benjamin Recht

This work presents GROUSE (Grassmanian Rank-One Update Subspace Estimation), an efficient online algorithm for tracking subspaces from highly incomplete observations. GROUSE requires only basic linear algebraic manipulat…

Matrix Completion