# Hide-and-Seek: A Data Augmentation Technique for Weakly-Supervised Localization and Beyond

arXiv: https://arxiv.org/abs/1811.02545 · HTML: https://mlsanity.com/paper/1811.02545/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Nov 2018.

## Built on by (most cited first, 30 of 36)

- [A Survey on Deep Semi-supervised Learning](https://mlsanity.com/paper/2103.00550/) (2021)
- [Mix3D: Out-of-Context Data Augmentation for 3D Scenes](https://mlsanity.com/paper/2110.02210/) (2021)
- [Image Data Augmentation for Deep Learning: A Survey](https://mlsanity.com/paper/2204.08610/) (2022)
- [TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers](https://mlsanity.com/paper/2207.08409/) (2022)
- [When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks](https://mlsanity.com/paper/2105.06152/) (2021)
- [MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks](https://mlsanity.com/paper/2103.06132/) (2021)
- [A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainability](https://mlsanity.com/paper/2212.10888/) (2022)
- [Survey: Image Mixing and Deleting for Data Augmentation](https://mlsanity.com/paper/2106.07085/) (2021)
- [Image Data Augmentation Approaches: A Comprehensive Survey and Future directions](https://mlsanity.com/paper/2301.02830/) (2023)
- [Enhancing 3D Lane Detection and Topology Reasoning with 2D Lane Priors](https://mlsanity.com/paper/2406.03105/) (2024)
- [Knowledge Transfer with Simulated Inter-Image Erasing for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2407.02768/) (2024)
- [ChessMix: Spatial Context Data Augmentation for Remote Sensing Semantic Segmentation](https://mlsanity.com/paper/2108.11535/) (2021)
- [Evolving Image Compositions for Feature Representation Learning](https://mlsanity.com/paper/2106.09011/) (2021)
- [Evolving to the Future: Unseen Event Adaptive Fake News Detection on Social Media](https://mlsanity.com/paper/2403.00037/) (2024)
- [Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange](https://mlsanity.com/paper/2404.07504/) (2024)
- [Domain Generalization for 6D Pose Estimation Through NeRF-based Image Synthesis](https://mlsanity.com/paper/2407.10762/) (2024)
- [Puzzles: Unbounded Video-Depth Augmentation for Scalable End-to-End 3D Reconstruction](https://mlsanity.com/paper/2506.23863/) (2025)
- [Evaluating COPY-BLEND Augmentation for Low Level Vision Tasks](https://mlsanity.com/paper/2103.05889/) (2021)
- [FAGC:Feature Augmentation on Geodesic Curve in the Pre-Shape Space](https://mlsanity.com/paper/2312.03325/) (2023)
- [Learning to Detour: Shortcut Mitigating Augmentation for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2405.18148/) (2024)
- [Effective Vision Transformer Training: A Data-Centric Perspective](https://mlsanity.com/paper/2209.15006/) (2022)
- [Domain Generalization for In-Orbit 6D Pose Estimation](https://mlsanity.com/paper/2406.11743/) (2024)
- [Exploring Stronger Transformer Representation Learning for Occluded Person Re-Identification](https://mlsanity.com/paper/2410.15613/) (2024)
- [Sharp Eyes: A Salient Object Detector Working The Same Way as Human Visual Characteristics](https://mlsanity.com/paper/2301.07431/) (2023)
- [MixCut:A Data Augmentation Method for Facial Expression Recognition](https://mlsanity.com/paper/2405.10489/) (2024)
- [BBoxCut: A Targeted Data Augmentation Technique for Enhancing Wheat Head Detection Under Occlusions](https://mlsanity.com/paper/2503.24032/) (2025)
- [MedCLM: Learning to Localize and Reason via a CoT-Curriculum in Medical Vision-Language Models](https://mlsanity.com/paper/2510.04477/) (2025)
- [Granular Ball Guided Masking: Structure-aware Data Augmentation](https://mlsanity.com/paper/2512.21011/) (2025)
- [PriorityCut: Occlusion-guided Regularization for Warp-based Image Animation](https://mlsanity.com/paper/2103.11600/) (2021)
- [Feature Weaken: Vicinal Data Augmentation for Classification](https://mlsanity.com/paper/2211.10944/) (2022)

## Abstract (arXiv)

We propose 'Hide-and-Seek' a general purpose data augmentation technique, which is complementary to existing data augmentation techniques and is beneficial for various visual recognition tasks. The key idea is to hide patches in a training image randomly, in order to force the network to seek other relevant content when the most discriminative content is hidden. Our approach only needs to modify the input image and can work with any network to improve its performance. During testing, it does not need to hide any patches. The main advantage of Hide-and-Seek over existing data augmentation techniques is its ability to improve object localization accuracy in the weakly-supervised setting, and we therefore use this task to motivate the approach. However, Hide-and-Seek is not tied only to the image localization task, and can generalize to other forms of visual input like videos, as well as other recognition tasks like image classification, temporal action localization, semantic segmentation, emotion recognition, age/gender estimation, and person re-identification. We perform extensive experiments to showcase the advantage of Hide-and-Seek on these various visual recognition problems.