litlas
Log inCreate account

Disentangling Factors of Variations Using Few Labels

Authors: Francesco Locatello, Michael Tschannen, Stefan Bauer, Gunnar Rätsch, Bernhard Schölkopf, Olivier Bachem - International Conference on Learning Representations, ICLR 2020 cited by 80

Learning disentangled representations is considered a cornerstone problem in representation learning. Recently, Locatello et al. (2019) demonstrated that unsupervised disentanglement learning without inductive biases is theoretically impossible and that existing inductive biases and unsupervised methods do not allow to consistently learn disentangled representations. However, in many practical settings, one might have access to a limited amount of supervision, for example through manual labeling of (some) factors of variation in a few training examples. In this paper, we investigate the impact of such supervision on state-of-the-art disentanglement methods and perform a large scale study, training over 52000 models under well-defined and reproducible experimental conditions. We observe that a small number of labeled examples (0.01--0.5\% of the data set), with potentially imprecise and incomplete labels, is sufficient to perform model selection on state-of-the-art unsupervised models. Further, we investigate the benefit of incorporating supervision into the training process. Overall, we empirically validate that with little and imprecise supervision it is possible to reliably learn disentangled representations.

Unsupervised FeatureLearning and Deep…Unsupervised Feature Learning and Deep Learning: A Review and New PerspectivesDeep VisualAnalogy-MakingDeep Visual Analogy-MakingDeep ConvolutionalInverse Graphics NetworkDeep Convolutional Inverse Graphics NetworkDeep learningDeep learningDisentangling factors ofvariation in deep…Disentangling factors of variation in deep representations using adversarial trainingDARLA: ImprovingZero-Shot Transfer in…DARLA: Improving Zero-Shot Transfer in Reinforcement LearningA Framework for theQuantitative Evaluation…A Framework for the Quantitative Evaluation of Disentangled RepresentationsRecent Advances inAutoencoder-Based…Recent Advances in Autoencoder-Based Representation LearningChallenging CommonAssumptions in the…Challenging Common Assumptions in the Unsupervised Learning of Disentangled RepresentationsOn the Transfer ofInductive Bias from…On the Transfer of Inductive Bias from Simulation to the Real World: a New Disentanglement DatasetDisentanglingDisentanglement in…Disentangling Disentanglement in Variational AutoencodersRobustly DisentangledCausal Mechanisms…Robustly Disentangled Causal Mechanisms: Validating Deep Representations for Interventional RobustnessAre DisentangledRepresentations Helpful…Are Disentangled Representations Helpful for Abstract Visual Reasoning?On the Transfer ofInductive Bias from…On the Transfer of Inductive Bias from Simulation to the Real World: a New Disentanglement DatasetRobustly DisentangledCausal Mechanisms…Robustly Disentangled Causal Mechanisms: Validating Deep Representations for Interventional RobustnessInfoGAN-CR andModelCentrality…InfoGAN-CR and ModelCentrality: Self-supervised Model Training and Selection for Disentangling GANsA Commentary on theUnsupervised Learning o…A Commentary on the Unsupervised Learning of Disentangled RepresentationsCausalVAE: StructuredCausal Disentanglement…CausalVAE: Structured Causal Disentanglement in Variational AutoencoderCausalVAE: DisentangledRepresentation Learning…CausalVAE: Disentangled Representation Learning via Neural Structural Causal ModelsLearning Causal SemanticRepresentation for…Learning Causal Semantic Representation for Out-of-Distribution PredictionLearning OptimalConditional Priors For…Learning Optimal Conditional Priors For Disentangled RepresentationsLearning disentangledrepresentations via…Learning disentangled representations via product manifold projectionMeasuringDisentanglement: A…Measuring Disentanglement: A Review of MetricsDesiderata forRepresentation Learning…Desiderata for Representation Learning: A Causal PerspectiveDisentangling Factors ofVariations Using Few…Disentangling Factors of Variations Using Few LabelsEarlier referencesFocus paperCiting papersOlderNewer

Click a node to pin it, click the empty canvas to go back to this paper, or hover to preview. Open a node’s page from its title.