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 251–275 of 1854 papers

TitleStatusHype
Fast Interpretable Greedy-Tree SumsCode1
Which Style Makes Me Attractive? Interpretable Control Discovery and Counterfactual Explanation on StyleGANCode1
Decompose to Adapt: Cross-domain Object Detection via Feature DisentanglementCode1
Image Disentanglement Autoencoder for Steganography Without EmbeddingCode1
Representation Topology Divergence: A Method for Comparing Neural Network RepresentationsCode1
Latte: Cross-framework Python Package for Evaluation of Latent-Based Generative ModelsCode1
Adverse Weather Image Translation with Asymmetric and Uncertainty-aware GANCode1
Interactive Disentanglement: Learning Concepts by Interacting with their Prototype RepresentationsCode1
SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and EditingCode1
Unsupervised Low-Light Image Enhancement via Histogram Equalization PriorCode1
Neural Emotion Director: Speech-preserving semantic control of facial expressions in "in-the-wild" videosCode1
Towards Principled Disentanglement for Domain GeneralizationCode1
Optimizing Latent Space Directions For GAN-based Local Image EditingCode1
3D Shape Variational Autoencoder Latent Disentanglement via Mini-Batch Feature Swapping for Bodies and FacesCode1
Towards Scalable Unpaired Virtual Try-On via Patch-Routed Spatially-Adaptive GANCode1
Self-supervised Re-renderable Facial Albedo Reconstruction from Single ImageCode1
Qimera: Data-free Quantization with Synthetic Boundary Supporting SamplesCode1
Unsupervised Learning of Compositional Energy ConceptsCode1
Generative Adversarial Graph Convolutional Networks for Human Action SynthesisCode1
Structural Characterization for Dialogue DisentanglementCode1
Toward a Visual Concept Vocabulary for GAN Latent SpaceCode1
Multimodal Emotion Recognition with High-level Speech and Text FeaturesCode1
Learning Temporally Latent Causal Processes from General Temporal DataCode1
DisUnknown: Distilling Unknown Factors for Disentanglement LearningCode1
Desiderata for Representation Learning: A Causal PerspectiveCode1
Show:102550
← PrevPage 11 of 75Next →

No leaderboard results yet.