SOTAVerified

Disentanglement

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)

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1061–1070 of 1854 papers

TitleStatusHype
Disentangled Speech Representation Learning Based on Factorized Hierarchical Variational Autoencoder with Self-Supervised Objective—0
Neural Convolutional Surfaces—0
IRON: Inverse Rendering by Optimizing Neural SDFs and Materials from Photometric Images—0
Shape-Pose Disentanglement using SE(3)-equivariant Vector NeuronsCode1
Learning Disentangled Semantic Representations for Zero-Shot Cross-Lingual Transfer in Multilingual Machine Reading ComprehensionCode1
Learning Disentangled Representations of Negation and UncertaintyCode0
TransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial EditingCode1
Robust Disentangled Variational Speech Representation Learning for Zero-shot Voice ConversionCode1
High-resolution Face Swapping via Latent Semantics DisentanglementCode1
CoordGAN: Self-Supervised Dense Correspondences Emerge from GANsCode1
Show:102550
← PrevPage 107 of 186Next →

No leaderboard results yet.