# Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation

arXiv: https://arxiv.org/abs/2012.07177 · HTML: https://mlsanity.com/paper/2012.07177/

## Key facts

- Cited by 596 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Dec 2020.

## Built on by (most cited first, 30 of 596)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [SimMIM: A Simple Framework for Masked Image Modeling](https://mlsanity.com/paper/2111.09886/) (2021)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model](https://mlsanity.com/paper/2401.09417/) (2024)
- [Exploring Plain Vision Transformer Backbones for Object Detection](https://mlsanity.com/paper/2203.16527/) (2022)
- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023)
- [EVA: Exploring the Limits of Masked Visual Representation Learning at Scale](https://mlsanity.com/paper/2211.07636/) (2022)
- [RegionCLIP: Region-based Language-Image Pretraining](https://mlsanity.com/paper/2112.09106/) (2021)
- [Detecting Twenty-thousand Classes using Image-level Supervision](https://mlsanity.com/paper/2201.02605/) (2022)
- [Vision Transformer Adapter for Dense Predictions](https://mlsanity.com/paper/2205.08534/) (2022)
- [MViTv2: Improved Multiscale Vision Transformers for Classification and Detection](https://mlsanity.com/paper/2112.01526/) (2021)
- [YOLOv10: Real-Time End-to-End Object Detection](https://mlsanity.com/paper/2405.14458/) (2024)
- [InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions](https://mlsanity.com/paper/2211.05778/) (2022)
- [Scaling Open-Vocabulary Image Segmentation with Image-Level Labels](https://mlsanity.com/paper/2112.12143/) (2021)
- [A Survey of Data Augmentation Approaches for NLP](https://mlsanity.com/paper/2105.03075/) (2021)
- [EVA-02: A Visual Representation for Neon Genesis](https://mlsanity.com/paper/2303.11331/) (2023)
- [Segment Anything in High Quality](https://mlsanity.com/paper/2306.01567/) (2023)
- [Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.04803/) (2023)
- [Bottleneck Transformers for Visual Recognition](https://mlsanity.com/paper/2101.11605/) (2021)
- [High-Performance Large-Scale Image Recognition Without Normalization](https://mlsanity.com/paper/2102.06171/) (2021)
- [Pix2seq: A Language Modeling Framework for Object Detection](https://mlsanity.com/paper/2109.10852/) (2021)
- [Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation](https://mlsanity.com/paper/2206.02777/) (2022)
- [Scaling Open-Vocabulary Object Detection](https://mlsanity.com/paper/2306.09683/) (2023)
- [OneFormer: One Transformer to Rule Universal Image Segmentation](https://mlsanity.com/paper/2211.06220/) (2022)
- [Simple Open-Vocabulary Object Detection with Vision Transformers](https://mlsanity.com/paper/2205.06230/) (2022)
- [MultiMAE: Multi-modal Multi-task Masked Autoencoders](https://mlsanity.com/paper/2204.01678/) (2022)

## Abstract (arXiv)

Building instance segmentation models that are data-efficient and can handle rare object categories is an important challenge in computer vision. Leveraging data augmentations is a promising direction towards addressing this challenge. Here, we perform a systematic study of the Copy-Paste augmentation ([13, 12]) for instance segmentation where we randomly paste objects onto an image. Prior studies on Copy-Paste relied on modeling the surrounding visual context for pasting the objects. However, we find that the simple mechanism of pasting objects randomly is good enough and can provide solid gains on top of strong baselines. Furthermore, we show Copy-Paste is additive with semi-supervised methods that leverage extra data through pseudo labeling (e.g. self-training). On COCO instance segmentation, we achieve 49.1 mask AP and 57.3 box AP, an improvement of +0.6 mask AP and +1.5 box AP over the previous state-of-the-art. We further demonstrate that Copy-Paste can lead to significant improvements on the LVIS benchmark. Our baseline model outperforms the LVIS 2020 Challenge winning entry by +3.6 mask AP on rare categories.