mlsanityData to 7 Oct 2026

Modeling Visual Context is Key to Augmenting Object Detection Datasets

arXiv 1807.07428 ↗First posted 19 Jul 2018cs.CVcited by 106

Not on the map. Why?

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.

Key facts. Cited by 106 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Jul 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 21; 2022: 29; 2023: 13; 2024: 21; 2025: 11; 2026: 11.

106 papers.

Sort:

By area:

  1. 2021Mix3D: Out-of-Context Data Augmentation for 3D Scenescited by 126
  2. 2023Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentationcited by 115
  3. 2022A Comprehensive Survey of Image Augmentation Techniques for Deep Learningcited by 95
  4. 2021Context Decoupling Augmentation for Weakly Supervised Semantic Segmentationcited by 69
  5. 2021Making Images Real Again: A Comprehensive Survey on Deep Image Compositioncited by 63
  6. 2023GeoDiffusion: Text-Prompted Geometric Control for Object Detection Data Generationcited by 56
  7. 2022Voxel Field Fusion for 3D Object Detectioncited by 50
  8. 2022X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusioncited by 49
  9. 2021Motion-aware Contrastive Video Representation Learning via Foreground-background Mergingcited by 45
  10. 2021Learning to Detect Every Thing in an Open Worldcited by 37
  11. 2023MosaicFusion: Diffusion Models as Data Augmenters for Large Vocabulary Instance Segmentationcited by 35
  12. 2022Unsupervised Pre-training for Temporal Action Localization Taskscited by 31
38 more
  1. 2021CarveMix: A Simple Data Augmentation Method for Brain Lesion Segmentationcited by 30
  2. 2021OPA: Object Placement Assessment Datasetcited by 28
  3. 2021Survey: Image Mixing and Deleting for Data Augmentationcited by 25
  4. 2022AcroFOD: An Adaptive Method for Cross-domain Few-shot Object Detectioncited by 25
  5. 2021Image Compositing for Segmentation of Surgical Tools without Manual Annotationscited by 23
  6. 2021Scale-aware Automatic Augmentation for Object Detectioncited by 23
  7. 2021When Pigs Fly: Contextual Reasoning in Synthetic and Natural Scenescited by 23
  8. 2023Context Understanding in Computer Vision: A Surveycited by 23
  9. 2024TaskCLIP: Extend Large Vision-Language Model for Task Oriented Object Detectioncited by 21
  10. 2022InsMix: Towards Realistic Generative Data Augmentation for Nuclei Instance Segmentationcited by 19
  11. 2022Self-Pair: Synthesizing Changes from Single Source for Object Change Detection in Remote Sensing Imagerycited by 19
  12. 2024Thinking Outside the BBox: Unconstrained Generative Object Compositingcited by 19
  13. 2021Exploring Geometric Consistency for Monocular 3D Object Detectioncited by 17
  14. 2022Zero-Query Transfer Attacks on Context-Aware Object Detectorscited by 17
  15. 2022DALL-E for Detection: Language-driven Compositional Image Synthesis for Object Detectioncited by 17
  16. 2024ODGEN: Domain-specific Object Detection Data Generation with Diffusion Modelscited by 17
  17. 2021Exploring Visual Context for Weakly Supervised Person Searchcited by 16
  18. 2021Weakly-Supervised Video Object Grounding via Causal Interventioncited by 13
  19. 2021Exploiting Multi-Object Relationships for Detecting Adversarial Attacks in Complex Scenescited by 12
  20. 2022Fast Object Placement Assessmentcited by 12
  21. 2022Amodal Cityscapes: A New Dataset, its Generation, and an Amodal Semantic Segmentation Challenge Baselinecited by 12
  22. 2023Gen2Det: Generate to Detectcited by 12
  23. 2023SIM: Semantic-aware Instance Mask Generation for Box-Supervised Instance Segmentationcited by 11
  24. 2021Self-Supervised Tracking via Target-Aware Data Synthesiscited by 10
  25. 2021A Comparative Review of Recent Few-Shot Object Detection Algorithmscited by 10
  26. 2023Beyond Generation: Harnessing Text to Image Models for Object Detection and Segmentationcited by 10
  27. 2025How far can we go with ImageNet for Text-to-Image generation?cited by 10
  28. 2022Self-supervised Transparent Liquid Segmentation for Robotic Pouringcited by 9
  29. 2021Characterizing and Improving the Robustness of Self-Supervised Learning through Background Augmentationscited by 8
  30. 2022Learning with Free Object Segments for Long-Tailed Instance Segmentationcited by 8
  31. 2023Real-Aug: Realistic Scene Synthesis for LiDAR Augmentation in 3D Object Detectioncited by 7
  32. 2025Common Inpainted Objects In-N-Out of Contextcited by 7
  33. 2022Towards Model Generalization for Monocular 3D Object Detectioncited by 6
  34. 2022Improving Crowded Object Detection via Copy-Pastecited by 6
  35. 2024Efficient 4D Radar Data Auto-labeling Method using LiDAR-based Object Detection Networkcited by 6
  36. 2025ReCon: Region-Controllable Data Augmentation with Rectification and Alignment for Object Detectioncited by 6
  37. 2022Towards Robust Part-aware Instance Segmentation for Industrial Bin Pickingcited by 5
  38. 2022Domain-guided data augmentation for deep learning on medical imagingcited by 5

50 most cited of 106 All 106 (JSON)