Papers › DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution

DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution

3 Jun 2020CVPR 2021 1arXiv:2006.02334archive 2025-07-28

Siyuan Qiao, Liang-Chieh Chen, Alan Yuille

Many modern object detectors demonstrate outstanding performances by using the mechanism of looking and thinking twice. In this paper, we explore this mechanism in the backbone design for object detection. At the macro level, we propose Recursive Feature Pyramid, which incorporates extra feedback connections from Feature Pyramid Networks into the bottom-up backbone layers. At the micro level, we propose Switchable Atrous Convolution, which convolves the features with different atrous rates and gathers the results using switch functions. Combining them results in DetectoRS, which significantly improves the performances of object detection. On COCO test-dev, DetectoRS achieves state-of-the-art 55.7% box AP for object detection, 48.5% mask AP for instance segmentation, and 50.0% PQ for panoptic segmentation. The code is made publicly available.

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

The archive's official repository (joe-siyuan-qiao/DetectoRS) was not harvested; the 4 samples below come from 1 community repository.

Syntology 4 code samples harvested from 1 repository linked to this paper: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 4 samples from 1 repository, 3 ran (3 with no instrument failure; 0 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 1 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

joe-siyuan-qiao/DetectoRS officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: not harvested report
FenHua/Robust_Logo_Detection mentioned on GitHubpytorchSyntology: not harvested report
TeamA2020/Practice mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
Vishal-V/tf-models mentioned on GitHubtfMITSyntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report
novav/DetectoRS_Colab Apache-2.0Syntology: not harvested 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

4 samples harvested: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 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.

3ran
1unverified

Licence: 0 of the 4 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 Vishal-V/tf-models. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

Vishal-V/tf-models community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
augment in 36 papers onlyBN/resnet_cifar.py ran MIT (permissive) · 454488534eefb92a · report fixture: signature img:EagerTensor/3/int, label:EagerTensor/0/int · returned tuple · level recorded 2026-09-24
normalize in 638 papers
census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket
onlyBN/resnet_cifar.py ran MIT (permissive) · 1498fe39a90c1c70 · report fixture: signature img:EagerTensor/4/int, label:EagerTensor/1/int · returned tuple · level recorded 2026-09-24
scheduler in 12 papers onlyBN/resnet_cifar.py ran fingerprinted MIT (permissive) · 02ec52619ce805da · report fixture: signature epoch:int/0/int, lr:float/0/float · returned float · level recorded 2026-09-24
download_data in 6 papers finegan/dataset.py unverified MIT (permissive) · cabdcb9cf748ec42 · report

Tasks

Instance SegmentationObjectObject DetectionPanoptic SegmentationSegmentationSemantic Segmentationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Instance Segmentation COCO test-dev DetectoRS (ResNeXt-101-64x4d, multi-scale) AP50 72.0 #28 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev DetectoRS (ResNeXt-101-64x4d, multi-scale) AP75 53.3 #28 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev DetectoRS (ResNeXt-101-64x4d, multi-scale) APL 61.5 #28 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev DetectoRS (ResNeXt-101-64x4d, multi-scale) APM 50.9 #28 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev DetectoRS (ResNeXt-101-64x4d, multi-scale) APS 31.6 #28 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev DetectoRS (ResNeXt-101-64x4d, multi-scale) mask AP 48.5 #28 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev DetectoRS (ResNeXt-101-32x4d, multi-scale) AP50 71.1 #33 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev DetectoRS (ResNeXt-101-32x4d, multi-scale) AP75 51.6 #33 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev DetectoRS (ResNeXt-101-32x4d, multi-scale) APL 59.6 #33 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev DetectoRS (ResNeXt-101-32x4d, multi-scale) APM 49.5 #33 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev DetectoRS (ResNeXt-101-32x4d, multi-scale) APS 30.3 #33 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev DetectoRS (ResNeXt-101-32x4d, multi-scale) mask AP 47.1 #33 of 112 Archive leaderboard report
Object Detection AI-TOD DetectoRS (ResNet-50-FPN) AP 14.8 #4 of 7 Archive leaderboard report
Object Detection AI-TOD DetectoRS (ResNet-50-FPN) AP50 32.8 #4 of 7 Archive leaderboard report
Object Detection AI-TOD DetectoRS (ResNet-50-FPN) AP75 11.4 #4 of 7 Archive leaderboard report
Object Detection AI-TOD DetectoRS (ResNet-50-FPN) APm 28.0 #4 of 7 Archive leaderboard report
Object Detection AI-TOD DetectoRS (ResNet-50-FPN) APs 28.3 #4 of 7 Archive leaderboard report
Object Detection AI-TOD DetectoRS (ResNet-50-FPN) APt 10.8 #4 of 7 Archive leaderboard report
Object Detection AI-TOD DetectoRS (ResNet-50-FPN) APvt 0.0 #4 of 7 Archive leaderboard report
Object Detection COCO test-dev DetectoRS (ResNeXt-101-64x4d, multi-scale) AP50 74.2 #48 of 225 Archive leaderboard report
Object Detection COCO test-dev DetectoRS (ResNeXt-101-64x4d, multi-scale) AP75 61.1 #48 of 225 Archive leaderboard report
Object Detection COCO test-dev DetectoRS (ResNeXt-101-64x4d, multi-scale) APL 68.1 #48 of 225 Archive leaderboard report
Object Detection COCO test-dev DetectoRS (ResNeXt-101-64x4d, multi-scale) APM 58.4 #48 of 225 Archive leaderboard report
Object Detection COCO test-dev DetectoRS (ResNeXt-101-64x4d, multi-scale) APS 37.7 #48 of 225 Archive leaderboard report
Object Detection COCO test-dev DetectoRS (ResNeXt-101-64x4d, multi-scale) box mAP 55.7 #48 of 225 Archive leaderboard report
Object Detection COCO test-dev DetectoRS (ResNeXt-101-32x4d, multi-scale) AP50 73.5 #53 of 225 Archive leaderboard report
Object Detection COCO test-dev DetectoRS (ResNeXt-101-32x4d, multi-scale) AP75 60.1 #53 of 225 Archive leaderboard report
Object Detection COCO test-dev DetectoRS (ResNeXt-101-32x4d, multi-scale) APL 66.4 #53 of 225 Archive leaderboard report
Object Detection COCO test-dev DetectoRS (ResNeXt-101-32x4d, multi-scale) APM 57.3 #53 of 225 Archive leaderboard report
Object Detection COCO test-dev DetectoRS (ResNeXt-101-32x4d, multi-scale) APS 37.4 #53 of 225 Archive leaderboard report
Object Detection COCO test-dev DetectoRS (ResNeXt-101-32x4d, multi-scale) box mAP 54.7 #53 of 225 Archive leaderboard report
Object Detection COCO test-dev DetectoRS (ResNeXt-101-32x4d, single-scale) AP50 71.6 #65 of 225 Archive leaderboard report
Object Detection COCO test-dev DetectoRS (ResNeXt-101-32x4d, single-scale) AP75 58.5 #65 of 225 Archive leaderboard report
Object Detection COCO test-dev DetectoRS (ResNeXt-101-32x4d, single-scale) APL 66.9 #65 of 225 Archive leaderboard report
Object Detection COCO test-dev DetectoRS (ResNeXt-101-32x4d, single-scale) APM 56.5 #65 of 225 Archive leaderboard report
Object Detection COCO test-dev DetectoRS (ResNeXt-101-32x4d, single-scale) APS 33.9 #65 of 225 Archive leaderboard report
Object Detection COCO test-dev DetectoRS (ResNeXt-101-32x4d, single-scale) box mAP 53.3 #65 of 225 Archive leaderboard report
Panoptic Segmentation COCO test-dev DetectoRS (ResNeXt-101-64x4d, multi-scale) PQ 50 #15 of 38 Archive leaderboard report
Panoptic Segmentation COCO test-dev DetectoRS (ResNeXt-101-64x4d, multi-scale) PQst 37.2 #15 of 38 Archive leaderboard report
Panoptic Segmentation COCO test-dev DetectoRS (ResNeXt-101-64x4d, multi-scale) PQth 58.5 #15 of 38 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

1x1 ConvolutionAverage PoolingConvolutionDilated ConvolutionGlobal Average PoolingRFPSACSigmoid 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