MIND-Net: A Deep Mutual Information Distillation Network for Realistic Low-Resolution Face Recognition

Cheng Yaw Low, Andrew Beng Jin Teoh, Jaewoo Park

Research output: Contribution to journalArticlepeer-review

16 Citations (Scopus)


Realistic low-resolution (LR) face images refer to those captured by the real-world surveillance cameras at extreme standoff distances, thereby LR and poor in quality essentially. Owing to severe scarcity of labeled data, a high-capacity deep convolution neural networks (CNN) is hardly trained to confront the realistic LR face recognition (LRFR) challenge. We introduce in this letter a dual-stream mutual information distillation network (MIND-Net), whereby the non-identity specific mutual information (MI) characterized by generic face features coexistent on realistic and synthetic LR face images are distilled to render a resolution-invariant embedding space for LRFR. For a thorough analysis, we quantify the degree of MI distillation in terms normalized MI index. Our experimental results on the realistic LR face datasets substantiate that the MIND-Net instances assembled from the pre-learned CNNs stand out from the baselines and other state of the arts by a notable margin.

Original languageEnglish
Article number9330619
Pages (from-to)354-358
Number of pages5
JournalIEEE Signal Processing Letters
Publication statusPublished - 2021

Bibliographical note

Publisher Copyright:
© 1994-2012 IEEE.

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Applied Mathematics
  • Electrical and Electronic Engineering


Dive into the research topics of 'MIND-Net: A Deep Mutual Information Distillation Network for Realistic Low-Resolution Face Recognition'. Together they form a unique fingerprint.

Cite this