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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1703.06211")

Code

Syntology Ran 3 of 9 code samples harvested from 4 repositories linked to this paper; 6 have no recorded run. Of those that ran: 1 ran · honoured contract; 2 ran · fixture could not drive it.

By repository: community (archive-listed): 9 samples from 4 repositories, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

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

msracver/Deformable-ConvNets officialmentioned in papermentioned on GitHubmxnetMIT report
DHZS/tf-deformable-conv-layer mentioned on GitHubtfMIT report
MonsterPeng/Deformable-ConvNets-master mentioned on GitHubtfApache-2.0 report
Mukosame/Zooming-Slow-Mo-CVPR-2020 mentioned on GitHubpytorchGPL-3.0 report
TangDL/DCN mentioned on GitHubtfMIT report
chenbys/GuidedOffset mentioned on GitHubtf report
esw0116/DynaVSR mentioned on GitHubpytorch report
fourmi1995/IronExperiment-DCN mentioned on GitHubmxnetMIT report
guanfuchen/Deformable-ConvNets mentioned on GitHubtfMIT report
hangg7/deformable-kernels mentioned on GitHubpytorchMIT report
hangg7/deformable-kernels mentioned on GitHubpytorchMIT report
makefile/frcnn mentioned on GitHub report
metaphorz/deep-image-prior-hqskipnet mentioned on GitHubpytorch report
necla-ml/Deformable-ConvNets-py3 mentioned on GitHubmxnetMIT report
oeway/pytorch-deform-conv mentioned on GitHubpytorch report
open-mmlab/mmsr mentioned on GitHubpytorchApache-2.0 report
qilei123/DEEPLAB_4_RETINA mentioned on GitHubtfMIT report
qilei123/DEEPLAB_4_RETINAIMG mentioned on GitHubtfMIT report
qilei123/DeformableConvV2 mentioned on GitHubmxnetMIT report
qilei123/DeformableConvV2_crop mentioned on GitHubmxnetMIT report
qilei123/fpn_crop mentioned on GitHubmxnetMIT report
qilei123/fpn_crop_v1_5d mentioned on GitHubmxnetMIT report
qilei123/sod_v1 mentioned on GitHubmxnetMIT report
qilei123/sod_v1_demo mentioned on GitHubmxnetMIT report
stupidZZ/pyc_repo mentioned on GitHubmxnetMIT report
tianhai123/deform-conv mentioned on GitHubtfMIT report
xiaoyongzhu/Deformable-ConvNets mentioned on GitHubmxnetApache-2.0 report
ximilar-com/xcenternet mentioned on GitHubtfMIT report
xinntao/EDVR mentioned on GitHubpytorch report
zengzhaoyang/Weak_Detection mentioned on GitHubtfMIT report
zengzhaoyang/trident mentioned on GitHubmxnetMIT report
zhusiling/EDVR mentioned on GitHubpytorchApache-2.0 report
zzdxfei/defor_conv_mxnet_code mentioned on GitHubmxnetMIT report
open-mmlab/mmdetection pytorchApache-2.0 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.

Code Syntology ran Syntology

9 samples harvested; 3 ran; 1 honoured the contract we drafted; 6 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
2ran · fixture could not drive it
6unverified

Licence: 3 of the 9 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 4 repositories linked to this paper, official or community; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

np_repeat_2d oeway/pytorch-deform-conv/torch_deform_conv/deform_conv.py community (archive-listed) ran · fixture could not drive it fingerprinted MIT (permissive) · 99464264d818eda2 · report
th_flatten oeway/pytorch-deform-conv/torch_deform_conv/deform_conv.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · 0ce99b2d4c408918 · report
th_repeat oeway/pytorch-deform-conv/torch_deform_conv/deform_conv.py community (archive-listed) ran · fixture could not drive it fingerprinted MIT (permissive) · 7d15625ab429830a · report
convert_context necla-ml/Deformable-ConvNets-py3/dcn/utils/load_model.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · 85b0d97b5f005697 · report
get_rcnn_names necla-ml/Deformable-ConvNets-py3/faster_rcnn/core/metric.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · bbf8005ce03c08cf · report
skip metaphorz/deep-image-prior-hqskipnet/models/skip.py community (archive-listed) unverified licence not identified · pointer only · 2d0d83b79a1d4a05 · report
tf_flatten tianhai123/deform-conv/deform_conv/deform_conv.py community (archive-listed) unverified MIT (permissive) · 12e6fdbf5080bbb4 · report
tf_repeat tianhai123/deform-conv/deform_conv/deform_conv.py community (archive-listed) unverified MIT (permissive) · 8a0d90e615ac2db1 · report
tf_repeat_2d tianhai123/deform-conv/deform_conv/deform_conv.py community (archive-listed) unverified MIT (permissive) · 89bffcebf8e96f1f · 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