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 1691–1700 of 1854 papers

TitleStatusHype
Disentangled GANs for Controllable Generation of High-Resolution Images—0
BasisVAE: Orthogonal Latent Space for Deep Disentangled Representation—0
RTC-VAE: HARNESSING THE PECULIARITY OF TOTAL CORRELATION IN LEARNING DISENTANGLED REPRESENTATIONS—0
Generating Multi-Sentence Abstractive Summaries of Interleaved Texts—0
OBJECT-ORIENTED REPRESENTATION OF 3D SCENES—0
Disentangling Improves VAEs' Robustness to Adversarial Attacks—0
Explicitly disentangling image content from translation and rotation with spatial-VAECode0
Generating Geological Facies Models with Fidelity to Diversity and Statistics of Training Images using Improved Generative Adversarial Networks—0
Cross-Dataset Person Re-Identification via Unsupervised Pose Disentanglement and Adaptation—0
Multi-mapping Image-to-Image Translation via Learning DisentanglementCode1
Show:102550
← PrevPage 170 of 186Next →

No leaderboard results yet.