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 341–350 of 1854 papers

TitleStatusHype
3D Shape Variational Autoencoder Latent Disentanglement via Mini-Batch Feature Swapping for Bodies and FacesCode1
A robust estimator of mutual information for deep learning interpretabilityCode1
Cross-Modal Conceptualization in Bottleneck ModelsCode1
Domain Knowledge-Informed Self-Supervised Representations for Workout Form AssessmentCode1
Domain-General Crowd Counting in Unseen ScenariosCode1
Multiple-Attribute Text Style TransferCode1
Multi-view Self-supervised Disentanglement for General Image DenoisingCode1
Music FaderNets: Controllable Music Generation Based On High-Level Features via Low-Level Feature ModellingCode1
Decoupled Textual Embeddings for Customized Image GenerationCode1
Dancing with Still Images: Video Distillation via Static-Dynamic DisentanglementCode1
Show:102550
← PrevPage 35 of 186Next →

No leaderboard results yet.