Deep networks for visual recognition are known to leverage "easy to recognise" portions of objects such as faces and distinctive texture patterns. The lack of a holistic understanding of objects may increase fragility and overfitting. In recent years, several papers have proposed to address this issue by means of occlusions as a form of data augmentation. However, successes have been limited to tasks such as weak localization and model interpretation, but no benefit was demonstrated on image classification on large-scale datasets. In this paper, we show that, by using a simple technique based on batch augmentation, occlusions as data augmentation can result in better performance on ImageNet for high-capacity models (e.g., ResNet50). We also show that varying amounts of occlusions used during training can be used to study the robustness of different neural network architectures.
@article{arxiv.1910.10651,
title = {Occlusions for Effective Data Augmentation in Image Classification},
author = {Ruth Fong and Andrea Vedaldi},
journal= {arXiv preprint arXiv:1910.10651},
year = {2019}
}
Comments
Accepted to 2019 ICCV Workshop on Interpreting and Explaining Visual Artificial Intelligence Models (v2: corrected references)