# FenceMask: A Data Augmentation Approach for Pre-extracted Image Features

arXiv: https://arxiv.org/abs/2006.07877 · HTML: https://mlsanity.com/paper/2006.07877/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jun 2020.

## Built on by (most cited first, 10 of 10)

- [Image Data Augmentation for Deep Learning: A Survey](https://mlsanity.com/paper/2204.08610/) (2022)
- [Expanding Small-Scale Datasets with Guided Imagination](https://mlsanity.com/paper/2211.13976/) (2022)
- [MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks](https://mlsanity.com/paper/2103.06132/) (2021)
- [MixBag: Bag-Level Data Augmentation for Learning from Label Proportions](https://mlsanity.com/paper/2308.08822/) (2023)
- [AdvMask: A Sparse Adversarial Attack Based Data Augmentation Method for Image Classification](https://mlsanity.com/paper/2211.16040/) (2022)
- [Enriching Information and Preserving Semantic Consistency in Expanding Curvilinear Object Segmentation Datasets](https://mlsanity.com/paper/2407.08209/) (2024)
- [BBoxCut: A Targeted Data Augmentation Technique for Enhancing Wheat Head Detection Under Occlusions](https://mlsanity.com/paper/2503.24032/) (2025)
- [SemAug: Semantically Meaningful Image Augmentations for Object Detection Through Language Grounding](https://mlsanity.com/paper/2208.07407/) (2022)
- [MaskAnyNet: Rethinking Masked Image Regions as Valuable Information in Supervised Learning](https://mlsanity.com/paper/2511.12480/) (2025)
- [Beyond Cropping and Rotation: Automated Evolution of Powerful Task-Specific Augmentations with Generative Models](https://mlsanity.com/paper/2602.03123/) (2026)

## Abstract (arXiv)

We propose a novel data augmentation method named 'FenceMask' that exhibits outstanding performance in various computer vision tasks. It is based on the 'simulation of object occlusion' strategy, which aim to achieve the balance between object occlusion and information retention of the input data. By enhancing the sparsity and regularity of the occlusion block, our augmentation method overcome the difficulty of small object augmentation and notably improve performance over baselines. Sufficient experiments prove the performance of our method is better than other simulate object occlusion approaches. We tested it on CIFAR10, CIFAR100 and ImageNet datasets for Coarse-grained classification, COCO2017 and VisDrone datasets for detection, Oxford Flowers, Cornel Leaf and Stanford Dogs datasets for Fine-Grained Visual Categorization. Our method achieved significant performance improvement on Fine-Grained Visual Categorization task and VisDrone dataset.