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 931–940 of 1854 papers

TitleStatusHype
CLIP-PAE: Projection-Augmentation Embedding to Extract Relevant Features for a Disentangled, Interpretable, and Controllable Text-Guided Face Manipulation—0
Multi-View Independent Component Analysis with Shared and Individual Sources—0
Collecting The Puzzle Pieces: Disentangled Self-Driven Human Pose Transfer by Permuting TexturesCode0
Evaluating Disentanglement in Generative Models Without Knowledge of Latent Factors—0
Compositional Generalization in Unsupervised Compositional Representation Learning: A Study on Disentanglement and Emergent Language—0
Zero-Shot Policy Transfer with Disentangled Task Representation of Meta-Reinforcement Learning—0
DCI-ES: An Extended Disentanglement Framework with Connections to IdentifiabilityCode0
Disentanglement with Biological Constraints: A Theory of Functional Cell Types—0
Training β-VAE by Aggregating a Learned Gaussian Posterior with a Decoupled DecoderCode0
StyleMask: Disentangling the Style Space of StyleGAN2 for Neural Face ReenactmentCode1
Show:102550
← PrevPage 94 of 186Next →

No leaderboard results yet.