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

Showing 341350 of 1854 papers

TitleStatusHype
3D Shape Variational Autoencoder Latent Disentanglement via Mini-Batch Feature Swapping for Bodies and FacesCode1
IntrinsicAvatar: Physically Based Inverse Rendering of Dynamic Humans from Monocular Videos via Explicit Ray TracingCode1
Cross-Modal Conceptualization in Bottleneck ModelsCode1
Is Disentanglement all you need? Comparing Concept-based & Disentanglement ApproachesCode1
On Disentangled Representations Learned From Correlated DataCode1
Isolating Sources of Disentanglement in Variational AutoencodersCode1
LADIS: Language Disentanglement for 3D Shape EditingCode1
Language-Informed Visual Concept LearningCode1
Cyclically Disentangled Feature Translation for Face Anti-spoofingCode1
Deciphering Spatio-Temporal Graph Forecasting: A Causal Lens and TreatmentCode1
Show:102550
← PrevPage 35 of 186Next →

No leaderboard results yet.