Papers › Deformable ConvNets v2: More Deformable, Better Results

Deformable ConvNets v2: More Deformable, Better Results

27 Nov 2018CVPR 2019 6arXiv:1811.11168archive 2025-07-28

Xizhou Zhu, Han Hu, Stephen Lin, Jifeng Dai

The superior performance of Deformable Convolutional Networks arises from its ability to adapt to the geometric variations of objects. Through an examination of its adaptive behavior, we observe that while the spatial support for its neural features conforms more closely than regular ConvNets to object structure, this support may nevertheless extend well beyond the region of interest, causing features to be influenced by irrelevant image content. To address this problem, we present a reformulation of Deformable ConvNets that improves its ability to focus on pertinent image regions, through increased modeling power and stronger training. The modeling power is enhanced through a more comprehensive integration of deformable convolution within the network, and by introducing a modulation mechanism that expands the scope of deformation modeling. To effectively harness this enriched modeling capability, we guide network training via a proposed feature mimicking scheme that helps the network to learn features that reflect the object focus and classification power of R-CNN features. With the proposed contributions, this new version of Deformable ConvNets yields significant performance gains over the original model and produces leading results on the COCO benchmark for object detection and instance segmentation.

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

Syntology 13 code samples harvested from 4 repositories linked to this paper: 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. 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): 13 samples from 4 repositories, 10 ran (9 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 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. 1 of the 10 samples that ran has no recorded date.

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

4uiiurz1/pytorch-deform-conv-v2 mentioned on GitHubpytorchMITSyntology: 8 samples, 5 ran (1 instrument-failed) · 3 unverified report
CS-GangXu/TMNet mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Temporal Modulation Network for Controllable Space-Time Video Super-Resolution (arXiv:2104.10642; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
Mukosame/Zooming-Slow-Mo-CVPR-2020 mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
chengdazhi/Deformable-Convolution-V2-PyTorch mentioned on GitHubpytorchMITSyntology: not harvested report
developer0hye/Simple-PyTorch-Deformable-Convolution-v2 mentioned on GitHubpytorchMITSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
eunjnnn/bfstvsr mentioned on GitHubpytorchSyntology: not harvested report
lyqcom/fasterrcnn-fpn-dcn mentioned on GitHubmindsporeApache-2.0Syntology: not harvested report
masamitsu-murase/deform_conv2d_onnx_exporter mentioned on GitHubpytorchSyntology: not harvested report
msracver/Deformable-ConvNets mentioned on GitHubmxnetMITSyntology: not harvested report
picsart-ai-research/videoinr-continuous-space-time-super-resolution mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time... (arXiv:2206.04647; that paper's own run record: 6 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
qilei123/DeformableConvV2 mentioned on GitHubmxnetMITSyntology: not harvested report
qilei123/DeformableConvV2_crop mentioned on GitHubmxnetMITSyntology: not harvested report
qilei123/fpn_crop mentioned on GitHubmxnetMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified 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: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
zengzhaoyang/trident mentioned on GitHubmxnetMITSyntology: not harvested report
zzangjinsun/NLSPN_ECCV20 mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Non-Local Spatial Propagation Network for Depth Completion (arXiv:2007.10042; that paper's own run record: 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) · 2 unverified); nothing checks that they implement this paper's method. report
zzdxfei/defor_conv_mxnet_code mentioned on GitHubmxnetMITSyntology: not harvested report
MindCode-4/code-3 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MathOdyssey: Benchmarking Mathematical Problem-Solving Skills in Large Language Models... (arXiv:2406.18321; 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) · 0 unverified); nothing checks that they implement this paper's method. report
MindSpore-paper-code-3/code8 mindsporeSyntology: not harvested report
MindSpore-scientific-2/code-4 mindsporeSyntology: not harvested report
MindSpore-scientific-2/code-5 mindsporeSyntology: not harvested report
PaddlePaddle/PaddleDetection paddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PP-YOLOE: An evolved version of YOLO (arXiv:2203.16250; that paper's own run record: 22 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 2 honoured, 0 violated, 17 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 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; 0 where Syntology's instrument failed) · 1 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

13 samples harvested: 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. “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
8ran
3unverified

Licence: 4 of the 13 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 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. 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.

4uiiurz1/pytorch-deform-conv-v2 community (archive-listed) 8 samples, 5 ran (1 instrument-failed) · 3 unverified
count_params in 80 papers utils.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · 616b5e82dd2a38f9 · report fixture: signature model:callable/0/? · returned int · level recorded, date not recorded
apply_transform in 12 papers scaled_mnist/dataset.py ran MIT (permissive) · d821268221317ba7 · report fixture: signature x:ndarray/3/float, transform_matrix:ndarray/2/float, channel_axis:int/0/int, fill_mode:str/0/str, cval:float/0/float · returned ndarray · level recorded 2026-09-26
random_zoom scaled_mnist/dataset.py ran MIT (permissive) · 535237e758ff9a2d · report fixture: signature X:ndarray/3/float, zoom_range:list/1/float, row_axis:int/0/int, col_axis:int/0/int, channel_axis:int/0/int, fill_mode:str/0/str, cval:float/0/float · returned ndarray · level recorded 2026-09-26
str2bool in 533 papers utils.py ran MIT (permissive) · 2e468cbd0d4a4241 · report fixture: signature v:str/0/str · returned bool · level recorded 2026-09-24
transform_matrix_offset_center in 11 papers scaled_mnist/dataset.py ran · our draft was wrong fingerprinted MIT (permissive) · 3c85a6426b383b41 · report fixture: signature matrix:ndarray/2/float, x:int/0/int, y:int/0/int · returned ndarray · level recorded 2026-09-22
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
utils.py unverified MIT (permissive) here; the stored copy is pointer only · 913d82af53065418 · report
train in 522 papers scaled_mnist_train.py unverified MIT (permissive) · 1c4389015d8afe22 · report
validate in 313 papers scaled_mnist_train.py unverified MIT (permissive) · d82090d852599504 · report
developer0hye/Simple-PyTorch-Deformable-Convolution-v2 community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
random_rotation in 15 papers offset_visualization.py ran MIT (permissive) · b9ffe70adbfccc8f · report fixture: signature img:ndarray/3/int, scale_factor:float/0/float, borderValue:int/0/int · returned ndarray · level recorded 2026-09-26
rotation_transformation offset_visualization.py ran MIT (permissive) · 68bd809d7357f434 · report fixture: signature img:ndarray/3/int, angle:float/0/float, borderValue:int/0/int · returned ndarray · level recorded 2026-09-26
scale_transformation offset_visualization.py ran MIT (permissive) · c6af90b54035ca62 · report fixture: signature img:ndarray/3/int, scale_factor:float/0/float, borderValue:int/0/int · returned ndarray · level recorded 2026-09-26
qilei123/fpn_crop community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
get_rcnn_names in 6 papers fpn/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
qilei123/sod_v1_demo community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
search_paths experiments/faster_rcnn/rcnn_demo.py ran fingerprinted MIT recorded; this copy not marked cleared · pointer only · d73fa5b90dd46680 · report fixture: signature path:str/0/str · returned list · level recorded 2026-09-26

Tasks

Instance SegmentationObjectObject DetectionSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection COCO minival Mask R-CNN (ResNet-101, DCNv2) box AP 43.1 #146 of 220 Archive leaderboard report
Object Detection COCO minival Faster R-CNN (ResNet-101, DCNv2) APL 58.7 #162 of 220 Archive leaderboard report
Object Detection COCO minival Faster R-CNN (ResNet-101, DCNv2) APM 45.8 #162 of 220 Archive leaderboard report
Object Detection COCO minival Faster R-CNN (ResNet-101, DCNv2) APS 22.2 #162 of 220 Archive leaderboard report
Object Detection COCO minival Faster R-CNN (ResNet-101, DCNv2) box AP 41.7 #162 of 220 Archive leaderboard report
Object Detection COCO test-dev DCNv2 (ResNet-101, multi-scale) AP50 67.9 #132 of 225 Archive leaderboard report
Object Detection COCO test-dev DCNv2 (ResNet-101, multi-scale) AP75 50.8 #132 of 225 Archive leaderboard report
Object Detection COCO test-dev DCNv2 (ResNet-101, multi-scale) APL 59.5 #132 of 225 Archive leaderboard report
Object Detection COCO test-dev DCNv2 (ResNet-101, multi-scale) APM 49.1 #132 of 225 Archive leaderboard report
Object Detection COCO test-dev DCNv2 (ResNet-101, multi-scale) APS 27.8 #132 of 225 Archive leaderboard report
Object Detection COCO test-dev DCNv2 (ResNet-101, multi-scale) box mAP 46.0 #132 of 225 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 PoolingBatch NormalizationBottleneck Residual BlockConvolutionDeformable ConvNetsDeformable ConvolutionDeformable RoI PoolingFaster R-CNNGlobal Average PoolingKaiming InitializationMask R-CNNMax PoolingNon Maximum SuppressionRPNReLUResidual BlockResidual ConnectionRoIAlignRoIPoolSGD with MomentumSoftmaxWeight Decay

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