An Implicit Identity-Extended Data Augmentation for Low-Resolution Face Representation Learning

Cheng Yaw Low, Andrew Beng-Jin Teoh

Research output: Contribution to journalArticlepeer-review


Low-resolution (LR) face recognition (LRFR) tackles tiny face images detected from real-world surveillance camera footage, which are unconstrained and generally poor in quality. Owing to the absence of a million-scale labeled LR face dataset, identity-invariant data augmentation (DA) transformations such as flipping, rotation, rescaling, etc., are applied to inflate the effective training examples with respect to the source identities for representation learning. Unfortunately, the identity-invariant property incurs additional intra-class disparity that impairs generalization performance. In this paper, we put forward a new means of DA strategy, termed identity-extended DA, that satisfies both affinity and diversity requirements essential to DA. We instantiate an implicit identity-extended augmentation network, or simply IDEA-Net, to realize the proposed identity-extended DA for LRFR. More specifically, training an IDEA-Net instance augments the small-scale LR (query) face dataset with identity-extended (auxiliary) face examples implicitly in the representation space. We also introduce a calibrator to regulate the disordered representation space by refining the intra-class compactness and the inter-class separation. This diminishes the distribution shift between the original and the augmented examples (affinity) and increases the learning complexity (diversity). We substantiate that IDEA-Net renders a high affinity and diversity representation space. On the other hand, our experimental results on three real-world LR face datasets demonstrate that IDEA-Nets outperform the baselines and other counterparts trained without leveraging the identity-extended examples for LRFR.

Original languageEnglish
Pages (from-to)3062-3076
Number of pages15
JournalIEEE Transactions on Information Forensics and Security
Publication statusPublished - 2022

Bibliographical note

Funding Information:
This work was supported in part by the Korea Research Fellowship (KRF) Program through the National Research Foundation of Korea (NRF) Grant funded by the Ministry of Science, and Information and Communications Technology (ICT) under Grant 2019H1D3A1A01101621, and the NRF Grant through the Korea government, the Ministry of Science ICT and Future Planning (MSIP) under Grant NRF-2022R1A2C1010710.

Publisher Copyright:
© 2022 IEEE.

All Science Journal Classification (ASJC) codes

  • Safety, Risk, Reliability and Quality
  • Computer Networks and Communications


Dive into the research topics of 'An Implicit Identity-Extended Data Augmentation for Low-Resolution Face Representation Learning'. Together they form a unique fingerprint.

Cite this