Abstract
The ImageNet dataset ushered in a flood of academic and industry interest in leveraging deep learning for computer vision applications. Despite the significant impact of the dataset on the field, there has not been a comprehensive investigation into the demographic attributes of the images contained within this dataset. Such an investigation could lead to new insights on inherent biases deep within the dataset, which is particularly important given it is frequently used to pretrain models for a wide variety of computer vision tasks. In this study, we introduce a model-driven framework for the automatic annotation of apparent age and gender attributes in large-scale image datasets. Using this framework, we conduct a comprehensive demographic audit of the 2012 ImageNet Large Scale Visual Recognition Challenge (ILSVRC) subset of ImageNet and the ‘person’ hierarchical category of ImageNet by studying the resulting annotations. We find that 41.62% of faces in ILSVRC appear as female, 1.71% appear as individuals above the age of 60, and males aged 15 to 29 account for the largest subgroup, at 27.11%. Such significant imbalances in the apparent demographics of ImageNet are important to identify so the indirect effects of such biases can be better studied. Code and annotations for this work are available at: this http URL
Abstract (translated by Google)
URL
http://arxiv.org/abs/1905.01347