Disentanglement
570 papers with code • 3 benchmarks • 12 datasets
This is an approach to solve a diverse set of tasks in a data efficient manner by disentangling (or isolating ) the underlying structure of the main problem into disjoint parts of its representations. This disentanglement can be done by focussing on the "transformation" properties of the world(main problem)
Libraries
Use these libraries to find Disentanglement models and implementationsDatasets
Most implemented papers
Interpreting the Latent Space of GANs for Semantic Face Editing
In this work, we propose a novel framework, called InterFaceGAN, for semantic face editing by interpreting the latent semantics learned by GANs.
Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning
Our method can also be used to embed real images into the disentangled latent space.
Measuring the Biases and Effectiveness of Content-Style Disentanglement
In this paper, we conduct an empirical study to investigate the role of different biases in content-style disentanglement settings and unveil the relationship between the degree of disentanglement and task performance.
ControlVAE: Tuning, Analytical Properties, and Performance Analysis
ControlVAE is a new variational autoencoder (VAE) framework that combines the automatic control theory with the basic VAE to stabilize the KL-divergence of VAE models to a specified value.
Stylized Neural Painting
Different from previous image-to-image translation methods that formulate the translation as pixel-wise prediction, we deal with such an artistic creation process in a vectorized environment and produce a sequence of physically meaningful stroke parameters that can be further used for rendering.
Multiple Heads are Better than One: Few-shot Font Generation with Multiple Localized Experts
MX-Font extracts multiple style features not explicitly conditioned on component labels, but automatically by multiple experts to represent different local concepts, e. g., left-side sub-glyph.
Disentangling factors of variation in deep representations using adversarial training
During training, the only available source of supervision comes from our ability to distinguish among different observations belonging to the same class.
A Large-Scale Corpus for Conversation Disentanglement
Disentangling conversations mixed together in a single stream of messages is a difficult task, made harder by the lack of large manually annotated datasets.
Multiple-Attribute Text Style Transfer
The dominant approach to unsupervised "style transfer" in text is based on the idea of learning a latent representation, which is independent of the attributes specifying its "style".
Deep Music Analogy Via Latent Representation Disentanglement
Analogy-making is a key method for computer algorithms to generate both natural and creative music pieces.