Papers › CBNet: A Novel Composite Backbone Network Architecture for Object Detection

CBNet: A Novel Composite Backbone Network Architecture for Object Detection

9 Sep 2019arXiv:1909.03625archive 2025-07-28

Yudong Liu, Yongtao Wang, Siwei Wang, Ting-Ting Liang, Qijie Zhao, Zhi Tang, Haibin Ling

In existing CNN based detectors, the backbone network is a very important component for basic feature extraction, and the performance of the detectors highly depends on it. In this paper, we aim to achieve better detection performance by building a more powerful backbone from existing backbones like ResNet and ResNeXt. Specifically, we propose a novel strategy for assembling multiple identical backbones by composite connections between the adjacent backbones, to form a more powerful backbone named Composite Backbone Network (CBNet). In this way, CBNet iteratively feeds the output features of the previous backbone, namely high-level features, as part of input features to the succeeding backbone, in a stage-by-stage fashion, and finally the feature maps of the last backbone (named Lead Backbone) are used for object detection. We show that CBNet can be very easily integrated into most state-of-the-art detectors and significantly improve their performances. For example, it boosts the mAP of FPN, Mask R-CNN and Cascade R-CNN on the COCO dataset by about 1.5 to 3.0 percent. Meanwhile, experimental results show that the instance segmentation results can also be improved. Specially, by simply integrating the proposed CBNet into the baseline detector Cascade Mask R-CNN, we achieve a new state-of-the-art result on COCO dataset (mAP of 53.3) with single model, which demonstrates great effectiveness of the proposed CBNet architecture. Code will be made available on https://github.com/PKUbahuangliuhe/CBNet.

PaperPDFCodeCode 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="1909.03625")

Code

Syntology Ran 0 of 4 code samples harvested from 2 repositories linked to this paper; 4 have no recorded run.

By repository: official repository: 3 samples from 1 repository, 0 ran; community (archive-listed): 1 sample from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

PKUbahuangliuhe/CBNet officialmentioned in papermentioned on GitHubcaffe2Apache-2.0 report
Adrian398/CB-Net-EDD mentioned on GitHubcaffe2Apache-2.0 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

4 samples harvested; 0 ran; 0 honoured the contract we drafted; 4 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.

4unverified

Licence: 1 of the 4 samples is 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 2 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.

add_VGG16_conv5_body PKUbahuangliuhe/CBNet/detectron/modeling/VGG16.py official repository unverified Apache-2.0 (permissive) · 867590b1664a9388 · report
add_VGG_CNN_M_1024_conv5_body PKUbahuangliuhe/CBNet/detectron/modeling/VGG_CNN_M_1024.py official repository unverified Apache-2.0 (permissive) · a7195f42969e79d3 · report
generate_anchors PKUbahuangliuhe/CBNet/detectron/modeling/generate_anchors.py official repository unverified Apache-2.0 (permissive) · 7b2d56f403fb4468 · report
get_model QiaoranC/tf_ResNeSt_RegNet_model/models/model_factory.py community (archive-listed) unverified no licence file found · pointer only · dfa5e9e748513c20 · report

Tasks

Instance SegmentationObject DetectionSemantic Segmentationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Instance Segmentation COCO test-dev Cascade Mask R-CNN (ResNeXt152, CBNet) mask AP 43.3 #49 of 112 Archive leaderboard report
Object Detection COCO test-dev Cascade Mask R-CNN (Triple-ResNeXt152, multi-scale) AP50 71.9 #64 of 225 Archive leaderboard report
Object Detection COCO test-dev Cascade Mask R-CNN (Triple-ResNeXt152, multi-scale) AP75 58.5 #64 of 225 Archive leaderboard report
Object Detection COCO test-dev Cascade Mask R-CNN (Triple-ResNeXt152, multi-scale) APL 66.7 #64 of 225 Archive leaderboard report
Object Detection COCO test-dev Cascade Mask R-CNN (Triple-ResNeXt152, multi-scale) APM 55.8 #64 of 225 Archive leaderboard report
Object Detection COCO test-dev Cascade Mask R-CNN (Triple-ResNeXt152, multi-scale) APS 35.5 #64 of 225 Archive leaderboard report
Object Detection COCO test-dev Cascade Mask R-CNN (Triple-ResNeXt152, multi-scale) box mAP 53.3 #64 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

Introduced by this paper: CBNet

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockCBNetCascade Mask R-CNNCascade R-CNNConvolutionFPNGlobal Average PoolingGrouped ConvolutionKaiming InitializationMask R-CNNMax PoolingRPNRandom Horizontal FlipReLUResNeXtResNeXt BlockResidual BlockResidual ConnectionRoIAlignSoftmax

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