Adversarial Capsule Autoencoder with Styles

Xiufeng Liu, Zhao Zhang, Yi Yang

Abstract:

Capsule networks get achievements in many computer vision tasks.
However, in the field of image generation, it has huge room for
improvement compared to the mainstream models. This is because
the capsule network can not fully parse useful features and has
limited capabilities of modeling the hierarchical and geometrical
structure of the object in background noise. In this paper, we propose a novel capsule autoencoder with viewpoint equivariance
characteristics that can learn the part-object spatial hierarchical
features, we dubbed it Adversarial Capsule Autoencoder with Styles
(Style-ACAE). Specifically, Style-ACAE first decomposes the object
into a set of semantic-consistent part-level descriptions and then
assembles them into object-level descriptions to build the hierarchy.
Furthermore, we effectively apply the modified generator structure,
which introduces novel style modulation and demodulation. The
new generator handles long-range dependency of part-object and
captures the global structure of the object. This is the first case
of the capsule network for image generation on commonly used
benchmarks. The experimental results show that Style-ACAE can
generate high-quality samples and has a competitive performance
to state-of-the-art generative models. And in some datasets, our
method obtains the best results.