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 201210 of 1854 papers

TitleStatusHype
Music Mixing Style Transfer: A Contrastive Learning Approach to Disentangle Audio EffectsCode1
Neural Systematic BinderCode1
A robust estimator of mutual information for deep learning interpretabilityCode1
DisenPOI: Disentangling Sequential and Geographical Influence for Point-of-Interest RecommendationCode1
FIND: An Unsupervised Implicit 3D Model of Articulated Human FeetCode1
p^3VAE: a physics-integrated generative model. Application to the pixel-wise classification of airborne hyperspectral imagesCode1
DyTed: Disentangled Representation Learning for Discrete-time Dynamic GraphCode1
AniFaceGAN: Animatable 3D-Aware Face Image Generation for Video AvatarsCode1
GAN You Hear Me? Reclaiming Unconditional Speech Synthesis from Diffusion ModelsCode1
StyleMask: Disentangling the Style Space of StyleGAN2 for Neural Face ReenactmentCode1
Show:102550
← PrevPage 21 of 186Next →

No leaderboard results yet.