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 301–350 of 1854 papers

TitleStatusHype
Exploring Gradient-based Multi-directional Controls in GANsCode1
Continual Learning for Text Classification with Information Disentanglement Based RegularizationCode1
Continuous Melody Generation via Disentangled Short-Term Representations and Structural ConditionsCode1
Deep Dimension Reduction for Supervised Representation LearningCode1
Fast Interpretable Greedy-Tree SumsCode1
FedDCSR: Federated Cross-domain Sequential Recommendation via Disentangled Representation LearningCode1
Attri-VAE: attribute-based interpretable representations of medical images with variational autoencodersCode1
Contrastive Learning Inverts the Data Generating ProcessCode1
Disentangled Contrastive Collaborative FilteringCode1
Fine-Tuning Attention Modules Only: Enhancing Weight Disentanglement in Task ArithmeticCode1
Audio-Driven Emotional Video PortraitsCode1
Deep Music Analogy Via Latent Representation DisentanglementCode1
A Latent Transformer for Disentangled Face Editing in Images and VideosCode1
GAN-Control: Explicitly Controllable GANsCode1
Disentangled Diffusion-Based 3D Human Pose Estimation with Hierarchical Spatial and Temporal DenoiserCode1
Generating Syntactically Controlled Paraphrases without Using Annotated Parallel PairsCode1
DisenPOI: Disentangling Sequential and Geographical Influence for Point-of-Interest RecommendationCode1
CluCDD:Contrastive Dialogue Disentanglement via ClusteringCode1
Diagonal Attention and Style-based GAN for Content-Style Disentanglement in Image Generation and TranslationCode1
GoHD: Gaze-oriented and Highly Disentangled Portrait Animation with Rhythmic Poses and Realistic ExpressionCode1
Grasping the Arrow of Time from the Singularity: Decoding Micromotion in Low-dimensional Latent Spaces from StyleGANCode1
Cooperative Sentiment Agents for Multimodal Sentiment AnalysisCode1
CoordGAN: Self-Supervised Dense Correspondences Emerge from GANsCode1
A Unified Model for Zero-shot Music Source Separation, Transcription and SynthesisCode1
MixRec: Heterogeneous Graph Collaborative FilteringCode1
Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive LearningCode1
AlphaPre: Amplitude-Phase Disentanglement Model for Precipitation NowcastingCode1
Counterfactual Generative Modeling with Variational Causal InferenceCode1
How Positive Are You: Text Style Transfer using Adaptive Style EmbeddingCode1
HSIC-InfoGAN: Learning Unsupervised Disentangled Representations by Maximising Approximated Mutual InformationCode1
Disentangled Face Attribute Editing via Instance-Aware Latent Space SearchCode1
Image Disentanglement Autoencoder for Steganography Without EmbeddingCode1
Image-to-image Translation via Hierarchical Style DisentanglementCode1
Improving Continuous Sign Language Recognition with Consistency Constraints and Signer RemovalCode1
DisDiff: Unsupervised Disentanglement of Diffusion Probabilistic ModelsCode1
A Max-Min Entropy Framework for Reinforcement LearningCode1
Information Bottleneck Disentanglement for Identity SwappingCode1
Ins-HOI: Instance Aware Human-Object Interactions RecoveryCode1
Barbie: Text to Barbie-Style 3D AvatarsCode1
IntrinsicAvatar: Physically Based Inverse Rendering of Dynamic Humans from Monocular Videos via Explicit Ray TracingCode1
3D Shape Variational Autoencoder Latent Disentanglement via Mini-Batch Feature Swapping for Bodies and FacesCode1
Investigation of F0 conditioning and Fully Convolutional Networks in Variational Autoencoder based Voice ConversionCode1
A robust estimator of mutual information for deep learning interpretabilityCode1
On Disentangled Representations Learned From Correlated DataCode1
JOKR: Joint Keypoint Representation for Unsupervised Cross-Domain Motion RetargetingCode1
L2M-GAN: Learning To Manipulate Latent Space Semantics for Facial Attribute EditingCode1
Understanding Latent Correlation-Based Multiview Learning and Self-Supervision: An Identifiability PerspectiveCode1
Latent Diffusion Autoencoders: Toward Efficient and Meaningful Unsupervised Representation Learning in Medical ImagingCode1
Cyclically Disentangled Feature Translation for Face Anti-spoofingCode1
DisenBooth: Identity-Preserving Disentangled Tuning for Subject-Driven Text-to-Image GenerationCode1
Show:102550
← PrevPage 7 of 38Next →

No leaderboard results yet.