Papers › Acquisition of Localization Confidence for Accurate Object Detection

Acquisition of Localization Confidence for Accurate Object Detection

30 Jul 2018ECCV 2018 9arXiv:1807.11590archive 2025-07-28

Borui Jiang, Ruixuan Luo, Jiayuan Mao, Tete Xiao, Yuning Jiang

Modern CNN-based object detectors rely on bounding box regression and non-maximum suppression to localize objects. While the probabilities for class labels naturally reflect classification confidence, localization confidence is absent. This makes properly localized bounding boxes degenerate during iterative regression or even suppressed during NMS. In the paper we propose IoU-Net learning to predict the IoU between each detected bounding box and the matched ground-truth. The network acquires this confidence of localization, which improves the NMS procedure by preserving accurately localized bounding boxes. Furthermore, an optimization-based bounding box refinement method is proposed, where the predicted IoU is formulated as the objective. Extensive experiments on the MS-COCO dataset show the effectiveness of IoU-Net, as well as its compatibility with and adaptivity to several state-of-the-art object detectors.

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

The archive's official repository (vacancy/PreciseRoIPooling) was not harvested; the 18 samples below come from 1 community repository.

Syntology 18 code samples harvested from 1 repository linked to this paper: 17 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 18 samples from 1 repository, 17 ran (13 with no instrument failure; 4 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 1 of its repositories that Syntology harvested for other papers:

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. 1 of the 17 samples that ran has no recorded date.

vacancy/PreciseRoIPooling officialmentioned in papermentioned on GitHubpytorchMITSyntology: not harvested report
CSAILVision/unifiedparsing mentioned on GitHubpytorchMITSyntology: 18 samples, 17 ran (4 instrument-failed) · 1 unverified report
Qinhj07/ATOMCode mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Mask R-CNN (arXiv:1703.06870; that paper's own run record: 101 ran (of which 3 constructed an object rather than computing a result; 77 with no instrument failure: 2 honoured, 1 violated, 74 with no contract checked; 24 where Syntology's instrument failed) · 39 unverified); nothing checks that they implement this paper's method. report
cameronthurston/CSAILVisionUpdated mentioned on GitHubpytorchSyntology: 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.

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

18 samples harvested: 17 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 4 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.

3ran · our draft was wrong
1ran; the contract check could not run
13ran
1unverified

Licence: 2 of the 18 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 CSAILVision/unifiedparsing. “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.

CSAILVision/unifiedparsing community (archive-listed) 18 samples, 17 ran (4 instrument-failed) · 1 unverified
build_histogram broden_dataset_utils/joint_dataset.py ran MIT (permissive) · 44ac53d5e92e8648 · report fixture: signature pairs:list/1/tuple, reducer:callable/0/? · returned dict · level recorded 2026-09-25
colorEncode utils.py ran MIT (permissive) · 84f0eba9ce9b82f0 · report fixture: signature labelmap:ndarray/2/int, colors:ndarray/2/int, mode:str/0/str · returned ndarray · level recorded 2026-09-25
conv3x3 in 1,376 papers models/resnet.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · fac5364e2f53c6db · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
conv3x3 in 1,376 papers models/models.py ran · our draft was wrong MIT (permissive) · dbcb53696bc43ef9 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, has_bias:bool/0/bool · returned Conv2d · level recorded 2026-09-22
decodeRG dataset.py ran MIT (permissive) · 8640d6f0031ac974 · report fixture: signature im:Tensor/3/int · returned Tensor · level recorded 2026-09-25
encodeRG dataset.py ran fingerprinted MIT (permissive) · 49ceae6eb684bd5f · report fixture: signature channel:ndarray/2/int · returned ndarray · level recorded 2026-09-25
get_records broden_dataset_utils/joint_dataset.py ran MIT (permissive) · cfb85a1616335f23 · report fixture: signature path:str/0/str · returned list · level recorded 2026-09-25
load_url in 9 papers models/resnext.py ran MIT (permissive) · a42beb0aba2deb89 · report fixture: signature url:str/0/str, model_dir:str/0/str, map_location:str/0/str · returned dict · level recorded 2026-09-25
map_in_pool resize_images.py ran MIT (permissive) · 17b987ef7da24e28 · report fixture: signature fn:callable/0/?, data:list/1/int, single_process:bool/0/bool, verbose:bool/0/bool · returned list · level recorded 2026-09-25
norm_name broden_dataset_utils/adeseg.py ran · our draft was wrong fingerprinted MIT (permissive) · 23d59f7c2061f932 · report fixture: signature s:str/0/str · returned str · level recorded 2026-09-25
norm_name broden_dataset_utils/osseg.py ran MIT (permissive) · 7ea70c61a8ecc9e3 · report fixture: signature s:str/0/str · returned str · level recorded 2026-09-25
resize_data_ade resize_images.py ran MIT (permissive) · dc7919eed93cbeb1 · report fixture: signature record:tuple/1/str, verbose:bool/0/bool · returned int · level recorded 2026-09-25
resize_data_os resize_images.py ran MIT (permissive) · 66ec50ed14ae3146 · report fixture: signature record:tuple/1/str, verbose:bool/0/bool · returned int · level recorded 2026-09-25
restore_csv broden_dataset_utils/joint_dataset.py ran MIT (permissive) · 42ef628a2975ab54 · report fixture: signature csv_path:str/0/str · returned list · level recorded 2026-09-25
round2nearest_multiple dataset.py ran fingerprinted MIT (permissive) · cc83fb3836123035 · report fixture: signature x:int/0/int, p:int/0/int · returned int · level recorded 2026-09-25
unique in 30 papers utils.py ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only · 5feabe579b35978a · report fixture: signature ar:ndarray/1/int, return_index:bool/0/bool, return_inverse:bool/0/bool, return_counts:bool/0/bool · returned tuple · level recorded 2026-09-25
wants broden_dataset_utils/dtdseg.py ran fingerprinted MIT (permissive) · 3bcef433d3ee1fc1 · report fixture: signature what:str/0/str, option:list/1/str · returned bool · level recorded 2026-09-25
MydrawMask utils.py unverified MIT (permissive) · 43b5123ff0f9f50a · report

Tasks

General ClassificationObjectObject Detectionobject-detectionregression

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection COCO test-dev IoU-Net box mAP 40.6 #192 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: IoU-Net, IoU-guided NMS, Precise RoI Pooling

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockCascade R-CNNConvolutionDense ConnectionsFPNGlobal Average PoolingIoU-NetIoU-guided NMSMask R-CNNMax PoolingPrecise RoI PoolingRPNReLUResidual BlockResidual ConnectionRoIAlignSGD with MomentumSoftmaxStep 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