Papers › Multiple Anchor Learning for Visual Object Detection

Multiple Anchor Learning for Visual Object Detection

4 Dec 2019CVPR 2020 6arXiv:1912.02252archive 2025-07-28

Wei Ke, Tianliang Zhang, Zeyi Huang, Qixiang Ye, Jianzhuang Liu, Dong Huang

Classification and localization are two pillars of visual object detectors. However, in CNN-based detectors, these two modules are usually optimized under a fixed set of candidate (or anchor) bounding boxes. This configuration significantly limits the possibility to jointly optimize classification and localization. In this paper, we propose a Multiple Instance Learning (MIL) approach that selects anchors and jointly optimizes the two modules of a CNN-based object detector. Our approach, referred to as Multiple Anchor Learning (MAL), constructs anchor bags and selects the most representative anchors from each bag. Such an iterative selection process is potentially NP-hard to optimize. To address this issue, we solve MAL by repetitively depressing the confidence of selected anchors by perturbing their corresponding features. In an adversarial selection-depression manner, MAL not only pursues optimal solutions but also fully leverages multiple anchors/features to learn a detection model. Experiments show that MAL improves the baseline RetinaNet with significant margins on the commonly used MS-COCO object detection benchmark and achieves new state-of-the-art detection performance compared with recent methods.

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 10 code samples harvested from 2 repositories linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 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): 10 samples from 2 repositories, 7 ran (6 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.

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

KevinKecc/MAL mentioned on GitHubpytorchSyntology: not harvested report
DeLightCMU/MAL pytorchMITSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
DeLightCMU/MAL-inference pytorchBSD-2-ClauseSyntology: 8 samples, 5 ran (0 instrument-failed) · 3 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

10 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
6ran
3unverified

Licence: 1 of the 10 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, 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.

DeLightCMU/MAL community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
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
smooth_l1_loss in 28 papers maskrcnn_benchmark/layers/smooth_l1_loss.py ran fingerprinted MIT (permissive) · e261fa29066b37e5 · report fixture: signature input:Tensor/2/float, target:Tensor/2/float, beta:float/0/float, size_average:bool/0/bool · returned Tensor · level recorded 2026-09-24
DeLightCMU/MAL-inference community (archive-listed) 8 samples, 5 ran (0 instrument-failed) · 3 unverified
box2delta retinanet/box.py ran fingerprinted BSD-2-Clause (permissive) · 6693e538e48a84c9 · report fixture: signature boxes:Tensor/2/float, anchors:Tensor/2/float · returned Tensor · level recorded 2026-09-24
convert_fixedbn_model retinanet/backbones/layers.py ran BSD-2-Clause (permissive) · 333799a2d6f1a170 · report fixture: signature module:callable/0/? · returned Sequential · level recorded 2026-09-24
delta2box1 retinanet/box.py ran BSD-2-Clause (permissive) · 7e0127e0e305eb71 · report fixture: signature rel_codes:Tensor/2/float, boxes:Tensor/2/float, weights:tuple/1/float, bbox_xform_clip:float/0/float · returned Tensor · level recorded 2026-09-24
generate_anchors in 19 papers retinanet/box.py ran BSD-2-Clause (permissive) · df48fc695a8a624c · report fixture: signature stride:int/0/int, ratio_vals:list/1/float, scales_vals:list/1/int · returned Tensor · level recorded 2026-09-24
show_detections retinanet/utils.py ran BSD-2-Clause (permissive) · deef1b581ac0b1ec · report fixture: signature detections:dict/0/? · returned Image · level recorded 2026-09-24
build_resnet_backbone retinanet/backbones/backbone.py unverified BSD-2-Clause (permissive) · 661727cf46a893a5 · report
build_resnet_fpn_backbone retinanet/backbones/backbone.py unverified BSD-2-Clause (permissive) · b8551d861a720f33 · report
build_resnet_fpn_p3p7_backbone retinanet/backbones/backbone.py unverified BSD-2-Clause (permissive) · 81c87c9068bdbd50 · report

Tasks

General ClassificationMultiple Instance LearningObjectObject Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection COCO test-dev MAL (ResNeXt101, multi-scale) box mAP 47.0 #122 of 225 Archive leaderboard report
Object Detection COCO test-dev MAL (ResNeXt101, single-scale) box mAP 45.9 #135 of 225 Archive leaderboard report
Object Detection COCO test-dev MAL (ResNet50, single-scale) box mAP 39.2 #207 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 ConvolutionConvolutionFPNFocal LossRetinaNet

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