Occlusions for Effective Data Augmentation in Image Classification
This addresses the issue of model fragility in image classification for computer vision researchers, but it is incremental as it builds on prior occlusion methods.
The paper tackled the problem of deep networks overfitting to easy-to-recognize object parts by using occlusions as data augmentation, and it demonstrated improved performance on ImageNet for high-capacity models like ResNet50 with concrete gains.
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.