Papers › DetNAS: Backbone Search for Object Detection

DetNAS: Backbone Search for Object Detection

26 Mar 2019NeurIPS 2019 12arXiv:1903.10979archive 2025-07-28

Yukang Chen, Tong Yang, Xiangyu Zhang, Gaofeng Meng, Xinyu Xiao, Jian Sun

Object detectors are usually equipped with backbone networks designed for image classification. It might be sub-optimal because of the gap between the tasks of image classification and object detection. In this work, we present DetNAS to use Neural Architecture Search (NAS) for the design of better backbones for object detection. It is non-trivial because detection training typically needs ImageNet pre-training while NAS systems require accuracies on the target detection task as supervisory signals. Based on the technique of one-shot supernet, which contains all possible networks in the search space, we propose a framework for backbone search on object detection. We train the supernet under the typical detector training schedule: ImageNet pre-training and detection fine-tuning. Then, the architecture search is performed on the trained supernet, using the detection task as the guidance. This framework makes NAS on backbones very efficient. In experiments, we show the effectiveness of DetNAS on various detectors, for instance, one-stage RetinaNet and the two-stage FPN. We empirically find that networks searched on object detection shows consistent superiority compared to those searched on ImageNet classification. The resulting architecture achieves superior performance than hand-crafted networks on COCO with much less FLOPs complexity.

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 8 code samples harvested from 1 repository linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 8 samples from 1 repository, 7 ran (5 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.

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

megvii-model/DetNAS officialmentioned in papermentioned on GitHubpytorchMITSyntology: 8 samples, 7 ran (2 instrument-failed) · 1 unverified report
open-mmlab/mmrazor pytorchApache-2.0Syntology: not harvested 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

8 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · our draft was wrong
5ran
1unverified

Licence: 3 of the 8 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 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 megvii-model/DetNAS. “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.

megvii-model/DetNAS official repository 8 samples, 7 ran (2 instrument-failed) · 1 unverified
channel_shuffle in 35 papers
census: 3 implementations from 7 papers, 2 distinct outputs on one shared input
Supernet-ImageNet/flops.py ran fingerprinted MIT (permissive) · eaa44944ca357418 · report fixture: signature x:Tensor/4/float · returned tuple · level recorded 2026-09-25
conv1x1_dwconv_conv1x1 Supernet-ImageNet/shuffle_blocks.py ran MIT (permissive) · 4686ee462c7a3786 · report fixture: signature prefix:str/0/str, in_channels:int/0/int, out_channels:int/0/int, mid_channels:int/0/int, kernel_size:int/0/int, stride:int/0/int, bn_training:bool/0/bool · returned Sequential · level recorded 2026-09-25
create_spatial_conv2d_group_bn_relu Supernet-ImageNet/shuffle_blocks.py ran MIT (permissive) · a3b5e54e37ce61d4 · report fixture: signature prefix:str/0/str, in_channels:int/0/int, out_channels:int/0/int, kernel_size:int/0/int, stride:int/0/int, padding:int/0/int, dilation:int/0/int, groups:int/0/int, bias:bool/0/bool, has_bn:bool/0/bool, has_relu:bool/0/bool, channel_shuffle:bool/0/bool, has_spatial_conv:bool/0/bool, has_spatial_conv_bn:bool/0/bool, conv_name_fun:NoneType/0/?, bn_name_fun:NoneType/0/?, bn_training:bool/0/bool, fix_weights:bool/0/bool · returned Sequential · level recorded 2026-09-25
get_flops in 14 papers Supernet-ImageNet/flops.py ran MIT (permissive) · 06193fa1714ef6fd · report fixture: signature model:callable/0/?, input_shape:tuple/1/int · returned int · level recorded 2026-09-25
get_parameters in 30 papers Supernet-ImageNet/utils.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 9a700a3b149f4952 · report fixture: signature model:callable/0/? · returned list · level recorded 2026-09-25
interpolate in 95 papers maskrcnn_benchmark/layers/misc.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 2902bf4410253ff7 · report fixture: signature input:Tensor/4/float, size:tuple/1/int, scale_factor:NoneType/0/?, mode:str/0/str, align_corners:NoneType/0/? · returned Tensor · level recorded 2026-09-25
xception in 13 papers Supernet-ImageNet/shuffle_blocks.py ran MIT (permissive) · 5e4726ccff0e0daf · report fixture: signature prefix:str/0/str, in_channels:int/0/int, out_channels:int/0/int, mid_channels:int/0/int, stride:int/0/int, bn_training:bool/0/bool · returned Sequential · level recorded 2026-09-25
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
Supernet-ImageNet/utils.py unverified MIT (permissive) here; the stored copy is pointer only · 469bf48752905889 · report

Tasks

General ClassificationImage ClassificationNeural Architecture SearchObjectObject Detectionimage-classificationobject-detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: DetNAS, DetNASNet

1x1 ConvolutionBatch NormalizationChannel ShuffleConvolutionDepthwise ConvolutionDetNASDetNASNetFPNFocal LossReLURetinaNetSGD with MomentumShuffleNet V2 BlockWeight 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