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

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

13 Dec 2020CVPR 2021 1arXiv:2012.07177archive 2025-07-28

Golnaz Ghiasi, Yin Cui, Aravind Srinivas, Rui Qian, Tsung-Yi Lin, Ekin D. Cubuk, Quoc V. Le, Barret Zoph

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.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

No sample from the archive's official repository (tensorflow/tpu) is linked to this paper; the 2 samples below come from 1 community repository. Syntology harvested code from tensorflow/tpu for another paper.

tensorflow/tpu: Syntology's graph links these samples to Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It (arXiv:2403.14715; that paper's own run record: 9 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method.

Syntology 2 code samples harvested from 1 repository linked to this paper: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 2 samples from 1 repository, 2 ran (1 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 3 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

tensorflow/tpu officialtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It (arXiv:2403.14715; that paper's own run record: 9 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
RocketFlash/CAP_augmentation mentioned on GitHubSyntology: not harvested report
conradry/copy-paste-aug mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
PaddlePaddle/PaddleOCR paddleApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to KRETA: A Benchmark for Korean Reading and Reasoning in Text-Rich VQA Attuned to... (arXiv:2508.19944; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
open-mmlab/mmdetection pytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to An Open and Comprehensive Pipeline for Unified Object Grounding and Detection (arXiv:2401.02361; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

2 samples harvested: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · our draft was wrong

Licence: 0 of the 2 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from conradry/copy-paste-aug. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

conradry/copy-paste-aug community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
extract_bboxes in 14 papers copy_paste.py ran · honoured contract MIT (permissive) · 7ea49e405e5dfb17 · report fixture: signature masks:list/1/ndarray · returned list · level recorded 2026-09-22
masks_copy_paste copy_paste.py ran · our draft was wrong fingerprinted MIT (permissive) · 64a6f51733860918 · report fixture: signature masks:list/1/ndarray, paste_masks:list/1/ndarray, alpha:ndarray/2/int · returned list · level recorded 2026-09-22

Tasks

Data AugmentationImage AugmentationInstance SegmentationObject DetectionSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Instance Segmentation COCO minival Cascade Eff-B7 NAS-FPN (1280, self-training Copy Paste, single-scale) mask AP 48.9 #31 of 93 Archive leaderboard report
Instance Segmentation COCO minival Cascade Eff-B7 NAS-FPN (1280) mask AP 46.8 #42 of 93 Archive leaderboard report
Instance Segmentation COCO test-dev Cascade Eff-B7 NAS-FPN (1280, self-training Copy Paste, single-scale) mask AP 49.1 #25 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev Cascade Eff-B7 NAS-FPN (1280) mask AP 46.9 #34 of 112 Archive leaderboard report
Instance Segmentation LVIS v1.0 val Eff-B7 NAS-FPN (1280, Copy-Paste pre-training)) mask AP 38.1 #11 of 25 Archive leaderboard report
Object Detection COCO minival Cascade Eff-B7 NAS-FPN (1280, self-training Copy Paste, single-scale) box AP 57.0 #43 of 220 Archive leaderboard report
Object Detection COCO minival Cascade Eff-B7 NAS-FPN (1280) box AP 54.5 #55 of 220 Archive leaderboard report
Object Detection COCO test-dev Cascade Eff-B7 NAS-FPN (1280, self-training Copy Paste, single-scale) box mAP 57.3 #37 of 225 Archive leaderboard report
Object Detection COCO test-dev Cascade Eff-B7 NAS-FPN (1280) box mAP 54.8 #52 of 225 Archive leaderboard report
Object Detection LVIS v1.0 val Eff-B7 NAS-FPN (1280, Copy-Paste pre-training)) box AP 41.6 #13 of 15 Archive leaderboard report
Object Detection PASCAL VOC 2007 Cascade Eff-B7 NAS-FPN (Copy Paste pre-training, single-scale) MAP 89.3% #1 of 30 Archive leaderboard report
Semantic Segmentation PASCAL VOC 2012 val Eff-B7 NAS-FPN (Copy-Paste pre-training, single-scale)) mIoU 86.6% #3 of 29 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: Copy-Paste

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockCascade Mask R-CNNConvolutionCopy-PasteDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionDropoutEfficientNetEntropy RegularizationGlobal Average PoolingInverted Residual BlockKaiming InitializationLSTMMask R-CNNMax PoolingNAS-FPNNeural Architecture SearchPPOPointwise ConvolutionRMSPropRPNReLUResidual BlockResidual ConnectionRoIAlignSigmoid ActivationSoftmaxSqueeze-and-Excitation BlockStochastic DepthTanh Activation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections