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 1181–1190 of 1854 papers

TitleStatusHype
Are disentangled representations all you need to build speaker anonymization systems?—0
Disentangled Speaker Representation Learning via Mutual Information Minimization—0
Disentangling Identity and Pose for Facial Expression Recognition—0
OrthoMAD: Morphing Attack Detection Through Orthogonal Identity DisentanglementCode0
Disentangled Representation Learning Using (β-)VAE and GAN—0
Disentangling 3D Attributes from a Single 2D Image: Human Pose, Shape and Garment—0
Latent Multi-Relation Reasoning for GAN-Prior based Image Super-Resolution—0
Equivariant Disentangled Transformation for Domain Generalization under Combination Shift—0
Zero-Shot Style Transfer for Gesture Animation driven by Text and Speech using Adversarial Disentanglement of Multimodal Style Encoding—0
Design What You Desire: Icon Generation from Orthogonal Application and Theme LabelsCode0
Show:102550
← PrevPage 119 of 186Next →

No leaderboard results yet.