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 1121–1130 of 1854 papers

TitleStatusHype
Which Style Makes Me Attractive? Interpretable Control Discovery and Counterfactual Explanation on StyleGANCode1
Domain Generalization via Frequency-domain-based Feature Disentanglement and Interaction—0
Towards Realistic Visual Dubbing with Heterogeneous Sources—0
Disentanglement enables cross-domain Hippocampus Segmentation—0
Enhancing Low-Light Images in Real World via Cross-Image Disentanglement—0
Self-Supervised Feature Learning from Partial Point Clouds via Pose Disentanglement—0
Decompose to Adapt: Cross-domain Object Detection via Feature DisentanglementCode1
Harmony: A Generic Unsupervised Approach for Disentangling Semantic Content From Parameterized Transformations—0
Rethinking Controllable Variational Autoencoders—0
BodyGAN: General-Purpose Controllable Neural Human Body Generation—0
Show:102550
← PrevPage 113 of 186Next →

No leaderboard results yet.