# Occlusions for Effective Data Augmentation in Image Classification

arXiv: https://arxiv.org/abs/1910.10651 · HTML: https://mlsanity.com/paper/1910.10651/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Oct 2019.

## Built on by (most cited first, 5 of 5)

- [Time to augment self-supervised visual representation learning](https://mlsanity.com/paper/2207.13492/) (2022)
- [ShapeAug: Occlusion Augmentation for Event Camera Data](https://mlsanity.com/paper/2401.02274/) (2024)
- [Improving Data-Efficient Fossil Segmentation via Model Editing](https://mlsanity.com/paper/2210.03879/) (2022)
- [Enhancing Image Classification with Augmentation: Data Augmentation Techniques for Improved Image Classification](https://mlsanity.com/paper/2502.18691/) (2025)
- [ShapeAug++: More Realistic Shape Augmentation for Event Data](https://mlsanity.com/paper/2409.11075/) (2024)

## Abstract (arXiv)

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.