Inferencing Based on Unsupervised Learning of Disentangled Representations
This addresses the challenge of unsupervised representation learning for tasks like image sampling with specific characteristics, but it appears incremental as it builds on existing GAN-based methods.
The paper tackles the problem of learning disentangled representations without labels by combining an encoder and a generator, and it shows that the encoder learns interpretable representations that can be used for inference on real and generated data.
Combining Generative Adversarial Networks (GANs) with encoders that learn to encode data points has shown promising results in learning data representations in an unsupervised way. We propose a framework that combines an encoder and a generator to learn disentangled representations which encode meaningful information about the data distribution without the need for any labels. While current approaches focus mostly on the generative aspects of GANs, our framework can be used to perform inference on both real and generated data points. Experiments on several data sets show that the encoder learns interpretable, disentangled representations which encode descriptive properties and can be used to sample images that exhibit specific characteristics.