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 121–130 of 1854 papers

TitleStatusHype
Arbitrary Style Transfer via Multi-Adaptation NetworkCode1
Architecture Disentanglement for Deep Neural NetworksCode1
Cross-Modal Conceptualization in Bottleneck ModelsCode1
A Unified Model for Zero-shot Music Source Separation, Transcription and SynthesisCode1
3D Shape Variational Autoencoder Latent Disentanglement via Mini-Batch Feature Swapping for Bodies and FacesCode1
Diverse 3D Hand Gesture Prediction from Body Dynamics by Bilateral Hand DisentanglementCode1
A Max-Min Entropy Framework for Reinforcement LearningCode1
Counterfactual Generative Modeling with Variational Causal InferenceCode1
Cyclically Disentangled Feature Translation for Face Anti-spoofingCode1
Adaptive Nonlinear Latent Transformation for Conditional Face EditingCode1
Show:102550
← PrevPage 13 of 186Next →

No leaderboard results yet.