# Data Augmentation for Object Detection via Progressive and Selective Instance-Switching

arXiv: https://arxiv.org/abs/1906.00358 · HTML: https://mlsanity.com/paper/1906.00358/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jun 2019.

## Built on by (most cited first, 18 of 18)

- [Distribution Alignment: A Unified Framework for Long-tail Visual Recognition](https://mlsanity.com/paper/2103.16370/) (2021)
- [Making Images Real Again: A Comprehensive Survey on Deep Image Composition](https://mlsanity.com/paper/2106.14490/) (2021)
- [OPA: Object Placement Assessment Dataset](https://mlsanity.com/paper/2107.01889/) (2021)
- [Scale-aware Automatic Augmentation for Object Detection](https://mlsanity.com/paper/2103.17220/) (2021)
- [Image Data Augmentation Approaches: A Comprehensive Survey and Future directions](https://mlsanity.com/paper/2301.02830/) (2023)
- [DiffusionEngine: Diffusion Model is Scalable Data Engine for Object Detection](https://mlsanity.com/paper/2309.03893/) (2023)
- [Exploring Geometric Consistency for Monocular 3D Object Detection](https://mlsanity.com/paper/2104.05858/) (2021)
- [Relaxed Equivariance via Multitask Learning](https://mlsanity.com/paper/2410.17878/) (2024)
- [LEMaRT: Label-Efficient Masked Region Transform for Image Harmonization](https://mlsanity.com/paper/2304.13166/) (2023)
- [Uncertainty-aware Unsupervised Multi-Object Tracking](https://mlsanity.com/paper/2307.15409/) (2023)
- [Offline-to-Online Knowledge Distillation for Video Instance Segmentation](https://mlsanity.com/paper/2302.07516/) (2023)
- [Traffic Context Aware Data Augmentation for Rare Object Detection in Autonomous Driving](https://mlsanity.com/paper/2205.00376/) (2022)
- [DiffPop: Plausibility-Guided Object Placement Diffusion for Image Composition](https://mlsanity.com/paper/2406.07852/) (2024)
- [D-Feat Occlusions: Diffusion Features for Robustness to Partial Visual Occlusions in Object Recognition](https://mlsanity.com/paper/2504.06432/) (2025)
- [ARUBA: An Architecture-Agnostic Balanced Loss for Aerial Object Detection](https://mlsanity.com/paper/2210.04574/) (2022)
- [Object Detection for Understanding Assembly Instruction Using Context-aware Data Augmentation and Cascade Mask R-CNN](https://mlsanity.com/paper/2101.02509/) (2021)
- [SemAug: Semantically Meaningful Image Augmentations for Object Detection Through Language Grounding](https://mlsanity.com/paper/2208.07407/) (2022)
- [GraPLUS: Graph-based Placement Using Semantics for Image Composition](https://mlsanity.com/paper/2503.15761/) (2025)

## Abstract (arXiv)

Collection of massive well-annotated samples is effective in improving object detection performance but is extremely laborious and costly. Instead of data collection and annotation, the recently proposed Cut-Paste methods [12, 15] show the potential to augment training dataset by cutting foreground objects and pasting them on proper new backgrounds. However, existing Cut-Paste methods cannot guarantee synthetic images always precisely model visual context, and all of them require external datasets. To handle above issues, this paper proposes a simple yet effective instance-switching (IS) strategy, which generates new training data by switching instances of same class from different images. Our IS naturally preserves contextual coherence in the original images while requiring no external dataset. For guiding our IS to obtain better object performance, we explore issues of instance imbalance and class importance in datasets, which frequently occur and bring adverse effect on detection performance. To this end, we propose a novel Progressive and Selective Instance-Switching (PSIS) method to augment training data for object detection. The proposed PSIS enhances instance balance by combining selective re-sampling with a class-balanced loss, and considers class importance by progressively augmenting training dataset guided by detection performance. The experiments are conducted on the challenging MS COCO benchmark, and results demonstrate our PSIS brings clear improvement over various state-of-the-art detectors (e.g., Faster R-CNN, FPN, Mask R-CNN and SNIPER), showing the superiority and generality of our PSIS. Code and models are available at: https://github.com/Hwang64/PSIS.