Back to Search
Start Over
Adversarial Learning of Disentangled and Generalizable Representations of Visual Attributes
- Source :
- IEEE Transactions on Neural Networks and Learning Systems. 33:3498-3509
- Publication Year :
- 2022
- Publisher :
- Institute of Electrical and Electronics Engineers (IEEE), 2022.
-
Abstract
- Recently, a multitude of methods for image-to-image translation have demonstrated impressive results on problems, such as multidomain or multiattribute transfer. The vast majority of such works leverages the strengths of adversarial learning and deep convolutional autoencoders to achieve realistic results by well-capturing the target data distribution. Nevertheless, the most prominent representatives of this class of methods do not facilitate semantic structure in the latent space and usually rely on binary domain labels for test-time transfer. This leads to rigid models, unable to capture the variance of each domain label. In this light, we propose a novel adversarial learning method that: 1) facilitates the emergence of latent structure by semantically disentangling sources of variation and 2) encourages learning generalizable, continuous, and transferable latent codes that enable flexible attribute mixing. This is achieved by introducing a novel loss function that encourages representations to result in uniformly distributed class posteriors for disentangled attributes. In tandem with an algorithm for inducing generalizable properties, the resulting representations can be utilized for a variety of tasks such as intensity-preserving multiattribute image translation and synthesis, without requiring labeled test data. We demonstrate the merits of the proposed method by a set of qualitative and quantitative experiments on popular databases such as MultiPIE, RaFD, and BU-3DFE, where our method outperforms other state-of-the-art methods in tasks such as intensity-preserving multiattribute transfer and synthesis.
- Subjects :
- Structure (mathematical logic)
Class (computer programming)
Computer Networks and Communications
Computer science
business.industry
media_common.quotation_subject
02 engineering and technology
Variation (game tree)
Machine learning
computer.software_genre
Computer Science Applications
Domain (software engineering)
Artificial Intelligence
0202 electrical engineering, electronic engineering, information engineering
Image translation
020201 artificial intelligence & image processing
Artificial intelligence
Set (psychology)
Function (engineering)
business
computer
Software
media_common
Test data
Subjects
Details
- ISSN :
- 21622388 and 2162237X
- Volume :
- 33
- Database :
- OpenAIRE
- Journal :
- IEEE Transactions on Neural Networks and Learning Systems
- Accession number :
- edsair.doi.dedup.....beff5cc2dcf9178d3e4ed98b17f4d2df