Cross-domain Prototype Learning from Contaminated Faces via Disentangling Latent Factors

Meng Pang, Binghui Wang, Shenbo Chen, Yiu-ming Cheung, Rong Zou, Wei Huang*

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review


This paper focuses on an emerging challenging problem called heterogeneous prototype learning (HPL) across face domains-It aims to learn the variation-free target domain prototype for a contaminated input image from the source domain and meanwhile preserve the personal identity. HPL involves two coupled subproblems, i.e., domain transfer and prototype learning. To address the two subproblems in a unified manner, we advocate disentangling the prototype and domain factors in their respected latent feature spaces, and replace the latent source domain features with the target domain ones to generate the heterogeneous prototype. To this end, we propose a disentangled heterogeneous prototype learning framework, dubbed DisHPL, which consists of one encoder-decoder generator and two discriminators. The generator and discriminators play adversarial games such that the generator learns to embed the contaminated image into a prototype feature space only capturing identity information and a domain-specific feature space, as well as generating a realistic-looking heterogeneous prototype. The two discriminators aim to predict personal identities and distinguish between real prototypes versus fake generated prototypes in the source/target domain. Experiments on various heterogeneous face datasets validate the effectiveness of DisHPL.
Original languageEnglish
Title of host publicationCIKM '22: Proceedings of the 31st ACM International Conference on Information & Knowledge Management
PublisherAssociation for Computing Machinery (ACM)
Number of pages5
ISBN (Print)9781450392365
Publication statusPublished - 17 Oct 2022
Event31st ACM International Conference on Information and Knowledge Management, CIKM 2022 - Atlanta, United States
Duration: 17 Oct 202221 Oct 2022


Conference31st ACM International Conference on Information and Knowledge Management, CIKM 2022
Country/TerritoryUnited States
Internet address

User-Defined Keywords

  • Heterogeneous prototype learning
  • heterogeneous face recognition
  • domain transfer
  • generative adversarial network


Dive into the research topics of 'Cross-domain Prototype Learning from Contaminated Faces via Disentangling Latent Factors'. Together they form a unique fingerprint.

Cite this