Image Ordinal Classification and Understanding: Grid Dropout with Masking Label

TL;DR

This paper introduces a grid dropout technique combined with masking labels for image ordinal classification, improving robustness and spatial awareness, especially on small datasets like Adience.

Contribution

It proposes a novel grid dropout method with masking labels that enhances spatial feature learning and robustness over traditional dropout and data augmentation methods.

Findings

Grid dropout improves spatial awareness in models.

The method outperforms state-of-the-art on age estimation.

Visualizations show better facial region focus.

Abstract

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 raining 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.