# Modeling Visual Context is Key to Augmenting Object Detection Datasets

arXiv: https://arxiv.org/abs/1807.07428 · HTML: https://mlsanity.com/paper/1807.07428/

## Key facts

- Cited by 106 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jul 2018.

## Built on by (most cited first, 30 of 106)

- [Mix3D: Out-of-Context Data Augmentation for 3D Scenes](https://mlsanity.com/paper/2110.02210/) (2021)
- [Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2305.00673/) (2023)
- [A Comprehensive Survey of Image Augmentation Techniques for Deep Learning](https://mlsanity.com/paper/2205.01491/) (2022)
- [Context Decoupling Augmentation for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2103.01795/) (2021)
- [Making Images Real Again: A Comprehensive Survey on Deep Image Composition](https://mlsanity.com/paper/2106.14490/) (2021)
- [GeoDiffusion: Text-Prompted Geometric Control for Object Detection Data Generation](https://mlsanity.com/paper/2306.04607/) (2023)
- [Voxel Field Fusion for 3D Object Detection](https://mlsanity.com/paper/2205.15938/) (2022)
- [X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusion](https://mlsanity.com/paper/2212.03863/) (2022)
- [Motion-aware Contrastive Video Representation Learning via Foreground-background Merging](https://mlsanity.com/paper/2109.15130/) (2021)
- [Learning to Detect Every Thing in an Open World](https://mlsanity.com/paper/2112.01698/) (2021)
- [MosaicFusion: Diffusion Models as Data Augmenters for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/2309.13042/) (2023)
- [Unsupervised Pre-training for Temporal Action Localization Tasks](https://mlsanity.com/paper/2203.13609/) (2022)
- [CarveMix: A Simple Data Augmentation Method for Brain Lesion Segmentation](https://mlsanity.com/paper/2108.06883/) (2021)
- [OPA: Object Placement Assessment Dataset](https://mlsanity.com/paper/2107.01889/) (2021)
- [Survey: Image Mixing and Deleting for Data Augmentation](https://mlsanity.com/paper/2106.07085/) (2021)
- [AcroFOD: An Adaptive Method for Cross-domain Few-shot Object Detection](https://mlsanity.com/paper/2209.10904/) (2022)
- [Image Compositing for Segmentation of Surgical Tools without Manual Annotations](https://mlsanity.com/paper/2102.09528/) (2021)
- [Scale-aware Automatic Augmentation for Object Detection](https://mlsanity.com/paper/2103.17220/) (2021)
- [When Pigs Fly: Contextual Reasoning in Synthetic and Natural Scenes](https://mlsanity.com/paper/2104.02215/) (2021)
- [Context Understanding in Computer Vision: A Survey](https://mlsanity.com/paper/2302.05011/) (2023)
- [TaskCLIP: Extend Large Vision-Language Model for Task Oriented Object Detection](https://mlsanity.com/paper/2403.08108/) (2024)
- [InsMix: Towards Realistic Generative Data Augmentation for Nuclei Instance Segmentation](https://mlsanity.com/paper/2206.15134/) (2022)
- [Self-Pair: Synthesizing Changes from Single Source for Object Change Detection in Remote Sensing Imagery](https://mlsanity.com/paper/2212.10236/) (2022)
- [Thinking Outside the BBox: Unconstrained Generative Object Compositing](https://mlsanity.com/paper/2409.04559/) (2024)
- [Exploring Geometric Consistency for Monocular 3D Object Detection](https://mlsanity.com/paper/2104.05858/) (2021)
- [Zero-Query Transfer Attacks on Context-Aware Object Detectors](https://mlsanity.com/paper/2203.15230/) (2022)
- [DALL-E for Detection: Language-driven Compositional Image Synthesis for Object Detection](https://mlsanity.com/paper/2206.09592/) (2022)
- [ODGEN: Domain-specific Object Detection Data Generation with Diffusion Models](https://mlsanity.com/paper/2405.15199/) (2024)
- [Exploring Visual Context for Weakly Supervised Person Search](https://mlsanity.com/paper/2106.10506/) (2021)
- [Weakly-Supervised Video Object Grounding via Causal Intervention](https://mlsanity.com/paper/2112.00475/) (2021)

## Abstract (arXiv)

Performing data augmentation for learning deep neural networks is well known to be important for training visual recognition systems. By artificially increasing the number of training examples, it helps reducing overfitting and improves generalization. For object detection, classical approaches for data augmentation consist of generating images obtained by basic geometrical transformations and color changes of original training images. In this work, we go one step further and leverage segmentation annotations to increase the number of object instances present on training data. For this approach to be successful, we show that modeling appropriately the visual context surrounding objects is crucial to place them in the right environment. Otherwise, we show that the previous strategy actually hurts. With our context model, we achieve significant mean average precision improvements when few labeled examples are available on the VOC'12 benchmark.