Image Ordinal Classification and Understanding: Grid Dropout with Masking Label

Chao Zhang, Ce Zhu, Jimin Xiao, Xun Xu*, Yipeng Liu

*Corresponding author for this work

Research output: Chapter in Book or Report/Conference proceedingConference Proceedingpeer-review

6 Citations (Scopus)


Image ordinal classification refers to predicting a discrete target value which carries ordering correlation among image categories. The limited size of labeled ordinal data renders modern deep learning approaches easy to overfit. To tackle this issue, neuron dropout and data augmentation were proposed which, however, still suffer from over-parameterization and breaking spatial structure, respectively. To address the issues, we first propose a grid dropout method that randomly dropout/blackout some areas of the training image. Then we combine the objective of predicting the blackout patches with classification to take advantage of the spatial information. Finally we demonstrate the effectiveness of both approaches by visualizing the Class Activation Map (CAM) and discover that grid dropout is more aware of the whole facial areas and more robust than neuron dropout for small training dataset. Experiments are conducted on a challenging age estimation dataset-Adience dataset with very competitive results compared with state-of-the-art methods.

Original languageEnglish
Title of host publication2018 IEEE International Conference on Multimedia and Expo, ICME 2018
PublisherIEEE Computer Society
ISBN (Electronic)9781538617373
Publication statusPublished - 8 Oct 2018
Event2018 IEEE International Conference on Multimedia and Expo, ICME 2018 - San Diego, United States
Duration: 23 Jul 201827 Jul 2018

Publication series

NameProceedings - IEEE International Conference on Multimedia and Expo
ISSN (Print)1945-7871
ISSN (Electronic)1945-788X


Conference2018 IEEE International Conference on Multimedia and Expo, ICME 2018
Country/TerritoryUnited States
CitySan Diego


  • Data Augmentation
  • Dropout
  • Ordinal Classification
  • Overfitting
  • Visualization

Cite this