Papers › Deformable Convolutional Networks

Deformable Convolutional Networks

17 Mar 2017ICCV 2017 10arXiv:1703.06211archive 2025-07-28

Jifeng Dai, Haozhi Qi, Yuwen Xiong, Yi Li, Guodong Zhang, Han Hu, Yichen Wei

Convolutional neural networks (CNNs) are inherently limited to model geometric transformations due to the fixed geometric structures in its building modules. In this work, we introduce two new modules to enhance the transformation modeling capacity of CNNs, namely, deformable convolution and deformable RoI pooling. Both are based on the idea of augmenting the spatial sampling locations in the modules with additional offsets and learning the offsets from target tasks, without additional supervision. The new modules can readily replace their plain counterparts in existing CNNs and can be easily trained end-to-end by standard back-propagation, giving rise to deformable convolutional networks. Extensive experiments validate the effectiveness of our approach on sophisticated vision tasks of object detection and semantic segmentation. The code would be released.

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 (msracver/Deformable-ConvNets) was not harvested; the 9 samples below come from 4 community repositories.

Syntology 9 code samples harvested from 4 repositories linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 9 samples from 4 repositories, 6 ran (4 with no instrument failure; 2 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 7 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

38 repositories listed; official and paper-mentioned ones first.

msracver/Deformable-ConvNets officialmentioned in papermentioned on GitHubmxnetMITSyntology: not harvested report
DHZS/tf-deformable-conv-layer mentioned on GitHubtfMITSyntology: not harvested report
MonsterPeng/Deformable-ConvNets-master mentioned on GitHubtfApache-2.0Syntology: not harvested report
Mukosame/Zooming-Slow-Mo-CVPR-2020 mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
NVIDIAAICITYCHALLENGE/AICity_Team6_ISU mentioned on GitHubtfSyntology: not harvested report
TangDL/DCN mentioned on GitHubtfMITSyntology: not harvested report
bkvie/Locally-Consistent-Deformable-Convolution mentioned on GitHubpytorchSyntology: not harvested report
chenbys/GuidedOffset mentioned on GitHubtfSyntology: not harvested report
esw0116/DynaVSR mentioned on GitHubpytorchSyntology: not harvested report
fourmi1995/IronExperiment-DCN mentioned on GitHubmxnetMITSyntology: not harvested report
guanfuchen/Deformable-ConvNets mentioned on GitHubtfMITSyntology: not harvested report
hangg7/deformable-kernels mentioned on GitHubpytorchMITSyntology: not harvested report
hangg7/deformable-kernels mentioned on GitHubpytorchMITSyntology: not harvested report
liyemei/Deformable-active-convolutional mentioned on GitHubSyntology: not harvested report
makefile/frcnn mentioned on GitHubSyntology: not harvested report
metaphorz/deep-image-prior-hqskipnet mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
necla-ml/Deformable-ConvNets-py3 mentioned on GitHubmxnetMITSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
oeway/pytorch-deform-conv mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (2 instrument-failed) · 0 unverified report
open-mmlab/mmsr mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to EDVR: Video Restoration with Enhanced Deformable Convolutional Networks (arXiv:1905.02716; that paper's own run record: 15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
qilei123/DEEPLAB_4_RETINA mentioned on GitHubtfMITSyntology: not harvested report
qilei123/DEEPLAB_4_RETINAIMG mentioned on GitHubtfMITSyntology: not harvested report
qilei123/DeformableConvV2 mentioned on GitHubmxnetMITSyntology: not harvested report
qilei123/DeformableConvV2_crop mentioned on GitHubmxnetMITSyntology: not harvested report
qilei123/fpn_crop mentioned on GitHubmxnetMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deformable ConvNets v2: More Deformable, Better Results (arXiv:1811.11168; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
qilei123/fpn_crop_v1_5d mentioned on GitHubmxnetMITSyntology: not harvested report
qilei123/sod_v1 mentioned on GitHubmxnetMITSyntology: not harvested report
qilei123/sod_v1_demo mentioned on GitHubmxnetMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deformable ConvNets v2: More Deformable, Better Results (arXiv:1811.11168; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
stupidZZ/pyc_repo mentioned on GitHubmxnetMITSyntology: not harvested report
tianhai123/deform-conv mentioned on GitHubtfMITSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
xiaoyongzhu/Deformable-ConvNets mentioned on GitHubmxnetApache-2.0Syntology: not harvested report
ximilar-com/xcenternet mentioned on GitHubtfMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Training-Time-Friendly Network for Real-Time Object Detection (arXiv:1909.00700; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
xinntao/EDVR mentioned on GitHubpytorchSyntology: not harvested report
zengzhaoyang/Weak_Detection mentioned on GitHubtfMITSyntology: not harvested report
zengzhaoyang/trident mentioned on GitHubmxnetMITSyntology: not harvested report
zhusiling/EDVR mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to EDVR: Video Restoration with Enhanced Deformable Convolutional Networks (arXiv:1905.02716; that paper's own run record: 15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
zzdxfei/defor_conv_mxnet_code mentioned on GitHubmxnetMITSyntology: 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
pytorch/vision pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Going Deeper with Convolutions (arXiv:1409.4842; that paper's own run record: 34 ran (of which 19 constructed an object rather than computing a result; 30 with no instrument failure: 1 honoured, 0 violated, 29 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified), Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Deep Networks with Stochastic Depth (arXiv:1603.09382; that paper's own run record: 8 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified) and 7 more (every one in this page's JSON twin); 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

9 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 3 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
2ran; the contract check could not run
3ran
3unverified

Licence: 4 of the 9 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 4 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

metaphorz/deep-image-prior-hqskipnet community (archive-listed) 1 sample, 0 ran · 1 unverified
skip in 14 papers models/skip.py unverified licence not identified · pointer only · 2d0d83b79a1d4a05 · report
necla-ml/Deformable-ConvNets-py3 community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
get_rcnn_names in 6 papers faster_rcnn/core/metric.py ran MIT recorded; this copy not marked cleared · pointer only · bbf8005ce03c08cf · report fixture: signature cfg:Config/0/? · returned tuple · level recorded 2026-09-25
convert_context dcn/utils/load_model.py unverified MIT recorded; this copy not marked cleared · pointer only · 85b0d97b5f005697 · report
oeway/pytorch-deform-conv community (archive-listed) 3 samples, 3 ran (2 instrument-failed) · 0 unverified
np_repeat_2d torch_deform_conv/deform_conv.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 99464264d818eda2 · report fixture: signature a:ndarray/2/int, repeats:int/0/int · returned ndarray · level recorded 2026-09-22
th_flatten torch_deform_conv/deform_conv.py ran · honoured contract fingerprinted MIT (permissive) · 0ce99b2d4c408918 · report fixture: signature a:Tensor/3/float · returned Tensor · level recorded 2026-09-22
th_repeat torch_deform_conv/deform_conv.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 7d15625ab429830a · report fixture: signature a:Tensor/1/float, repeats:int/0/int, axis:int/0/int · returned Tensor · level recorded 2026-09-22
tianhai123/deform-conv community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
tf_repeat deform_conv/deform_conv.py ran MIT (permissive) · 8a0d90e615ac2db1 · report fixture: signature a:SymbolicTensor/1/float, repeats:int/0/int, axis:int/0/int · returned EagerTensor · level recorded 2026-09-26
tf_repeat_2d deform_conv/deform_conv.py ran MIT (permissive) · 89bffcebf8e96f1f · report fixture: signature a:EagerTensor/2/float, repeats:int/0/int · returned EagerTensor · level recorded 2026-09-26
tf_flatten deform_conv/deform_conv.py unverified MIT (permissive) here; the stored copy is pointer only · 12e6fdbf5080bbb4 · report

Tasks

Object DetectionSemantic SegmentationVessel Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection COCO test-dev DeformConv-R-FCN (Aligned-Inception-ResNet) AP50 58.0 #218 of 225 Archive leaderboard report
Object Detection COCO test-dev DeformConv-R-FCN (Aligned-Inception-ResNet) APL 52.5 #218 of 225 Archive leaderboard report
Object Detection COCO test-dev DeformConv-R-FCN (Aligned-Inception-ResNet) APM 40.1 #218 of 225 Archive leaderboard report
Object Detection COCO test-dev DeformConv-R-FCN (Aligned-Inception-ResNet) APS 19.4 #218 of 225 Archive leaderboard report
Object Detection COCO test-dev DeformConv-R-FCN (Aligned-Inception-ResNet) box mAP 37.5 #218 of 225 Archive leaderboard report
Vessel Detection Vessel detection Dateset Deformable DETR AP 54.8% #3 of 3 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: Deformable ConvNets, Deformable Convolution, Deformable Position-Sensitive RoI Pooling, Deformable RoI Pooling

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionDeformable ConvNetsDeformable ConvolutionDeformable Position-Sensitive RoI PoolingDeformable RoI PoolingGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual Connection

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