Papers › Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applications

Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applications

11 Jan 2024CVPR 2024 1arXiv:2401.06197archive 2025-07-28

Yuwen Xiong, Zhiqi Li, Yuntao Chen, Feng Wang, Xizhou Zhu, Jiapeng Luo, Wenhai Wang, Tong Lu, Hongsheng Li, Yu Qiao, Lewei Lu, Jie zhou, Jifeng Dai

We introduce Deformable Convolution v4 (DCNv4), a highly efficient and effective operator designed for a broad spectrum of vision applications. DCNv4 addresses the limitations of its predecessor, DCNv3, with two key enhancements: 1. removing softmax normalization in spatial aggregation to enhance its dynamic property and expressive power and 2. optimizing memory access to minimize redundant operations for speedup. These improvements result in a significantly faster convergence compared to DCNv3 and a substantial increase in processing speed, with DCNv4 achieving more than three times the forward speed. DCNv4 demonstrates exceptional performance across various tasks, including image classification, instance and semantic segmentation, and notably, image generation. When integrated into generative models like U-Net in the latent diffusion model, DCNv4 outperforms its baseline, underscoring its possibility to enhance generative models. In practical applications, replacing DCNv3 with DCNv4 in the InternImage model to create FlashInternImage results in up to 80% speed increase and further performance improvement without further modifications. The advancements in speed and efficiency of DCNv4, combined with its robust performance across diverse vision tasks, show its potential as a foundational building block for future vision models.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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 18 code samples harvested from 2 repositories linked to this paper: 12 ran (of which 2 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 12 samples from 1 repository, 7 ran (3 with no instrument failure; 4 where Syntology's instrument failed); community (archive-listed): 6 samples from 1 repository, 5 ran (5 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.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

opengvlab/dcnv4 officialmentioned in papermentioned on GitHubpytorchMITSyntology: 12 samples, 7 ran (4 instrument-failed) · 5 unverified report
chenller/mmseg-extension mentioned on GitHubpytorchSyntology: 6 samples, 5 ran (0 instrument-failed) · 1 unverified 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

18 samples harvested: 12 ran (of which 2 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
4ran · our draft was wrong
6ran
6unverified

Licence: 6 of the 18 samples are pointer only, meaning Syntology does not serve that copy's text. For 6 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 2 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.

opengvlab/dcnv4 official repository 12 samples, 7 ran (4 instrument-failed) · 5 unverified
allreduce_hook classification/ddp_hooks.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · bb1a26fe42d7075c · report fixture: signature process_group:callable/0/?, bucket:callable/0/? · returned Mock · level recorded 2026-09-25
bf16_compress_hook classification/ddp_hooks.py ran MIT (permissive) here; the stored copy is pointer only · 21bd5be56c8f79d0 · report fixture: returned Mock · level recorded 2026-09-25
build_scheduler in 56 papers classification/lr_scheduler.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 07e8b4b487c0abb6 · report fixture: signature config:SimpleNamespace/0/?, optimizer:SGD/0/?, n_iter_per_epoch:int/0/int · returned LinearLRScheduler · level recorded 2026-09-25
create_logger in 172 papers classification/logger.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 80450600f7f09b0a · report fixture: signature output_dir:str/0/str, dist_rank:int/0/int, name:str/0/str · returned Logger · level recorded 2026-09-25
findspec DCNv4_op/DCNv4/functions/flash_deform_attn_func.py ran MIT (permissive) · 1c0a5794f6556b80 · report fixture: signature B:int/0/int, Q:int/0/int, G:int/0/int, C:int/0/int · returned tuple · level recorded 2026-09-24
findspec_bwd DCNv4_op/DCNv4/functions/flash_deform_attn_func.py ran MIT (permissive) · 13649542907b646c · report fixture: signature B:int/0/int, Q:int/0/int, G:int/0/int, C:int/0/int · returned tuple · level recorded 2026-09-24
fp16_compress_hook classification/ddp_hooks.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 26bfffb625dfe211 · report fixture: signature process_group:callable/0/?, bucket:callable/0/? · returned Mock · level recorded 2026-09-25
find_spec_bwd DCNv4_op/DCNv4/functions/dcnv4_func.py unverified MIT (permissive) · 297f5dc3b864f8ca · report
findspec DCNv4_op/DCNv4/functions/dcnv4_func.py unverified MIT (permissive) · 9c57b9e5a08a964c · report
get_config in 203 papers classification/config.py unverified MIT (permissive) here; the stored copy is pointer only · e452206cf1a59c19 · report
main in 235 papers classification/extract_feature.py unverified MIT (permissive) · 67cdd6568078cc51 · report
rgetattr in 22 papers classification/extract_feature.py unverified MIT (permissive) · 44925cf3831bfe79 · report
chenller/mmseg-extension community (archive-listed) 6 samples, 5 ran (0 instrument-failed) · 1 unverified
CenterFeatureScaleModule mmsegextlib/dcnv4/mmsegextlib_dcnv4/modules/dcnv4.py ran Apache-2.0 (permissive) · d82968bff87f113b · report fixture: signature query:Tensor/3/float, center_feature_scale_proj_weight:Tensor/2/float, center_feature_scale_proj_bias:Tensor/1/float · returned Tensor · level recorded 2026-09-24
DCNv4 mmsegextlib/dcnv4/mmsegextlib_dcnv4/modules/dcnv4.py ran Apache-2.0 (permissive) · d4124ae005136b98 · report fixture: returned DCNv4 · level recorded 2026-09-22
DCNv4Function mmsegextlib/dcnv4/mmsegextlib_dcnv4/modules/dcnv4.py ran Apache-2.0 (permissive) · ce961555262652ff · report fixture: returned DCNv4Function · level recorded 2026-09-22
factors mmsegextlib/dcnv4/mmsegextlib_dcnv4/modules/dcnv4.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · c9b8eed480765ae8 · report fixture: signature N:int/0/int · returned list · level recorded 2026-09-22
findspec mmsegextlib/dcnv4/mmsegextlib_dcnv4/modules/dcnv4.py ran · honoured contract Apache-2.0 (permissive) · 20c4614598af707f · report fixture: signature B:int/0/int, H:int/0/int, W:int/0/int, G:int/0/int, C:int/0/int · returned tuple · level recorded 2026-09-22
find_spec_bwd mmsegextlib/dcnv4/mmsegextlib_dcnv4/modules/dcnv4.py unverified Apache-2.0 (permissive) · a626f0d745b8c280 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Deformable Convolution v4 (DCNv4) (graph method: Deformable Convolution v4 (DCNv4)). 6 bricks; individually on a fixture: 5 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

  1. DCNv4 entry · level 1 · ran · d4124ae005136b98
  2. CenterFeatureScaleModule helper · level 1 · ran · d82968bff87f113b
  3. DCNv4Function helper · level 1 · ran · ce961555262652ff
  4. find_spec_bwd helper · level 0 · unverified · a626f0d745b8c280
  5. findspec helper · level 1 · ran · honoured contract · 20c4614598af707f
  6. factors helper · level 1 · ran · honoured contract · c9b8eed480765ae8

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2401.06197") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image ClassificationImage GenerationSemantic Segmentationimage-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Concatenated Skip ConnectionConvolutionDeformable ConvolutionDiffusionMax PoolingReLUSPEEDSoftmaxU-Net

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