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 191200 of 1854 papers

TitleStatusHype
LADIS: Language Disentanglement for 3D Shape EditingCode1
iQuery: Instruments as Queries for Audio-Visual Sound SeparationCode1
Cyclically Disentangled Feature Translation for Face Anti-spoofingCode1
Domain-General Crowd Counting in Unseen ScenariosCode1
Linear Causal Disentanglement via InterventionsCode1
Progressive Disentangled Representation Learning for Fine-Grained Controllable Talking Head SynthesisCode1
CDDSA: Contrastive Domain Disentanglement and Style Augmentation for Generalizable Medical Image SegmentationCode1
Face Swapping as A Simple Arithmetic OperationCode1
NeRFFaceEditing: Disentangled Face Editing in Neural Radiance FieldsCode1
Learning Causal Representations of Single Cells via Sparse Mechanism Shift ModelingCode1
Show:102550
← PrevPage 20 of 186Next →

No leaderboard results yet.