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 376–400 of 1854 papers

TitleStatusHype
Make Your Actor Talk: Generalizable and High-Fidelity Lip Sync with Motion and Appearance Disentanglement—0
Asynchronous Voice Anonymization Using Adversarial Perturbation On Speaker Embedding—0
A Concept-Based Explainability Framework for Large Multimodal ModelsCode1
Self-Distilled Disentangled Learning for Counterfactual PredictionCode0
Prioritizing Potential Wetland Areas via Region-to-Region Knowledge Transfer and Adaptive Propagation—0
DifAttack++: Query-Efficient Black-Box Adversarial Attack via Hierarchical Disentangled Feature Space in Cross-DomainCode1
Domain Game: Disentangle Anatomical Feature for Single Domain Generalized Segmentation—0
Enhancing Fairness in Unsupervised Graph Anomaly Detection through DisentanglementCode0
MultiPly: Reconstruction of Multiple People from Monocular Video in the Wild—0
Information Maximization via Variational Autoencoders for Cross-Domain Recommendation—0
Comparing the information content of probabilistic representation spacesCode0
A Comprehensive Survey on Underwater Image Enhancement Based on Deep LearningCode0
Multi-Aspect Controllable Text Generation with Disentangled Counterfactual AugmentationCode1
Metadata-guided Feature Disentanglement for Functional GenomicsCode0
3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting—0
AttenCraft: Attention-guided Disentanglement of Multiple Concepts for Text-to-Image CustomizationCode0
DualContrast: Unsupervised Disentangling of Content and Transformations with Implicit Parameterization—0
Diffusion Bridge AutoEncoders for Unsupervised Representation Learning—0
VOODOO XP: Expressive One-Shot Head Reenactment for VR Telepresence—0
Boost UAV-based Ojbect Detection via Scale-Invariant Feature Disentanglement and Adversarial Learning—0
ParamReL: Learning Parameter Space Representation via Progressively Encoding Bayesian Flow NetworksCode0
Sparse Expansion and Neuronal DisentanglementCode1
FreeTuner: Any Subject in Any Style with Training-free Diffusion—0
Crocodile: Cross Experts Covariance for Disentangled Learning in Multi-Domain Recommendation—0
RemoCap: Disentangled Representation Learning for Motion Capture—0
Show:102550
← PrevPage 16 of 75Next →

No leaderboard results yet.