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 881–890 of 1854 papers

TitleStatusHype
DSDRNet: Disentangling Representation and Reconstruct Network for Domain Generalization—0
DrFER: Learning Disentangled Representations for 3D Facial Expression Recognition—0
Controllable Face Aging—0
Human-aligned Deep Learning: Explainability, Causality, and Biological Inspiration—0
An Identity-Preserved Framework for Human Motion Transfer—0
Disentangled3D: Learning a 3D Generative Model with Disentangled Geometry and Appearance from Monocular Images—0
DreamLight: Towards Harmonious and Consistent Image Relighting—0
Disentangled 3D Scene Generation with Layout Learning—0
Controllable Data Generation Via Iterative Data-Property Mutual Mappings—0
Information Maximization via Variational Autoencoders for Cross-Domain Recommendation—0
Show:102550
← PrevPage 89 of 186Next →

No leaderboard results yet.