Learning Disentangled Representations with Reference-Based Variational Autoencoders
Learning disentangled representations from visual data, where different high-level generative factors are independently encoded, is of importance for many computer vision tasks. Solving this problem, however, typically requires to explicitly label all the factors of interest in training images. To alleviate the annotation cost, we introduce a learning setting which we refer to as "reference-based disentangling". Given a pool of unlabeled images, the goal is to learn a representation where a set of target factors are disentangled from others. The only supervision comes from an auxiliary "reference set" containing images where the factors of interest are constant. In order to address this problem, we propose reference-based variational autoencoders, a novel deep generative model designed to exploit the weak-supervision provided by the reference set. By addressing tasks such as feature learning, conditional image generation or attribute transfer, we validate the ability of the proposed model to learn disentangled representations from this minimal form of supervision.
Code (0)
등록된 구현이 없습니다.
Tasks
AttributeConditional Image GenerationImage GenerationSimilar Papers 제목 키워드 기반
Reference-based Variational Autoencoders
Learning disentangled representations from visual data, where different high-level generative factors are independently encoded, is of importance for many computer vision tasks. Solving this problem, however, typically r…
AttributeConditional Image GenerationImage GenerationHow do Variational Autoencoders Learn? Insights from Representational Similarity
The ability of Variational Autoencoders (VAEs) to learn disentangled representations has made them popular for practical applications. However, their behaviour is not yet fully understood. For example, the questions of w…
On Disentanglement in Gaussian Process Variational Autoencoders
Complex multivariate time series arise in many fields, ranging from computer vision to robotics or medicine. Often we are interested in the independent underlying factors that give rise to the high-dimensional data we ar…
DisentanglementTime SeriesTime Series AnalysisSinging Voice Conversion with Disentangled Representations of Singer and Vocal Technique Using Variational Autoencoders
We propose a flexible framework that deals with both singer conversion and singers vocal technique conversion. The proposed model is trained on non-parallel corpora, accommodates many-to-many conversion, and leverages re…
DecoderVoice ConversionPRI-VAE: Principle-of-Relevant-Information Variational Autoencoders
Although substantial efforts have been made to learn disentangled representations under the variational autoencoder (VAE) framework, the fundamental properties to the dynamics of learning of most VAE models still remain …