HP-Capsule: Unsupervised Face Part Discovery by Hierarchical Parsing Capsule Network

TL;DR

This paper introduces HP-Capsule, an unsupervised hierarchical capsule network that discovers face subparts and parts, enabling face segmentation and understanding without labels, extending capsule networks beyond digits to faces.

Contribution

The paper proposes a novel Hierarchical Parsing Capsule Network (HP-Capsule) for unsupervised face part discovery using a Transformer-based parsing module, advancing capsule network applications.

Findings

Effective face subpart and part discovery demonstrated on BP4D and Multi-PIE datasets.

Unsupervised face segmentation achieved with qualitative and quantitative results.

Extends capsule networks from digit recognition to complex face structures.

Abstract

Capsule networks are designed to present the objects by a set of parts and their relationships, which provide an insight into the procedure of visual perception. Although recent works have shown the success of capsule networks on simple objects like digits, the human faces with homologous structures, which are suitable for capsules to describe, have not been explored. In this paper, we propose a Hierarchical Parsing Capsule Network (HP-Capsule) for unsupervised face subpart-part discovery. When browsing large-scale face images without labels, the network first encodes the frequently observed patterns with a set of explainable subpart capsules. Then, the subpart capsules are assembled into part-level capsules through a Transformer-based Parsing Module (TPM) to learn the compositional relations between them. During training, as the face hierarchy is progressively built and refined, the part capsules adaptively encode the face parts with semantic consistency. HP-Capsule extends the application of capsule networks from digits to human faces and takes a step forward to show how the neural networks understand homologous objects without human intervention. Besides, HP-Capsule gives unsupervised face segmentation results by the covered regions of part capsules, enabling qualitative and quantitative evaluation. Experiments on BP4D and Multi-PIE datasets show the effectiveness of our method.