Papers › Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression

Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression

19 Nov 2019arXiv:1911.08287archive 2025-07-28

Zhaohui Zheng, Ping Wang, Wei Liu, Jinze Li, Rongguang Ye, Dongwei Ren

Bounding box regression is the crucial step in object detection. In existing methods, while ℓₙ-norm loss is widely adopted for bounding box regression, it is not tailored to the evaluation metric, i.e., Intersection over Union (IoU). Recently, IoU loss and generalized IoU (GIoU) loss have been proposed to benefit the IoU metric, but still suffer from the problems of slow convergence and inaccurate regression. In this paper, we propose a Distance-IoU (DIoU) loss by incorporating the normalized distance between the predicted box and the target box, which converges much faster in training than IoU and GIoU losses. Furthermore, this paper summarizes three geometric factors in bounding box regression, i.e., overlap area, central point distance and aspect ratio, based on which a Complete IoU (CIoU) loss is proposed, thereby leading to faster convergence and better performance. By incorporating DIoU and CIoU losses into state-of-the-art object detection algorithms, e.g., YOLO v3, SSD and Faster RCNN, we achieve notable performance gains in terms of not only IoU metric but also GIoU metric. Moreover, DIoU can be easily adopted into non-maximum suppression (NMS) to act as the criterion, further boosting performance improvement. The source code and trained models are available at https://github.com/Zzh-tju/DIoU.

PaperPDFCodeCode 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 (Zzh-tju/DIoU) was not harvested; the 24 samples below come from 5 community repositories, and 1 more is identical to code Syntology harvested from another paper's repository.

Syntology 25 code samples: 24 from 5 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 25: 17 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 0 violated, 13 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 2 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): 24 samples from 5 repositories, 16 ran (14 with no instrument failure; 2 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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 4 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

20 repositories listed; official and paper-mentioned ones first.

Zzh-tju/DIoU officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
DataXujing/DIoU_YOLO_V3 mentioned on GitHubpaddleGPL-3.0Syntology: not harvested report
RuiminChen/GIou_loss_caffe mentioned on GitHubSyntology: not harvested report
RuiminChen/GIouloss_CIouloss_caffe mentioned on GitHubSyntology: not harvested report
Zzh-tju/CIoU mentioned on GitHubpytorchSyntology: 2 samples, 0 ran · 2 unverified report
Zzh-tju/DIoU-SSD-pytorch mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
Zzh-tju/DIoU-darknet mentioned on GitHubGPL-3.0Syntology: not harvested report
Zzh-tju/DIoU-pytorch-detectron mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
Zzh-tju/ultralytics-YOLOv3-Cluster-NMS mentioned on GitHubpytorchSyntology: 3 samples, 2 ran (1 instrument-failed) · 1 unverified report
frgfm/Holocron mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to U-Net: Convolutional Networks for Biomedical Image Segmentation (arXiv:1505.04597; that paper's own run record: 530 ran (of which 247 constructed an object rather than computing a result; 378 with no instrument failure: 18 honoured, 10 violated, 350 with no contract checked; 152 where Syntology's instrument failed) · 227 unverified), Large Batch Training of Convolutional Networks (arXiv:1708.03888; that paper's own run record: 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 4 samples that ran constructed an object rather than computing a result), UNet++: A Nested U-Net Architecture for Medical Image Segmentation (arXiv:1807.10165; that paper's own run record: 21 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 1 honoured, 1 violated, 16 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified) and 3 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
gau-nernst/CenterNet mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense... (arXiv:2006.04388; that paper's own run record: 22 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 1 honoured, 0 violated, 20 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
grifon-239/diploma mentioned on GitHubtfMITSyntology: 15 samples, 11 ran (0 instrument-failed) · 4 unverified report
hll110/DIoU-darknet-master mentioned on GitHubnot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-readySyntology: not harvested report
lilanxiao/Rotated_IoU mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
maudzung/Complex-YOLOv4-Pytorch mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
symoon94/YOLO-keras mentioned on GitHubtfMITSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
CoinCheung/pytorch-loss pytorchSyntology: not harvested report
Mind23-2/MindCode-177 mindsporeSyntology: not harvested report
PaddlePaddle/PaddleDetection paddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PP-YOLOE: An evolved version of YOLO (arXiv:2203.16250; that paper's own run record: 22 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 2 honoured, 0 violated, 17 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
wangermeng2021/Scaled-YOLOv4-tensorflow2 tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Sharpness-Aware Minimization for Efficiently Improving Generalization (arXiv:2010.01412; that paper's own run record: 15 ran (of which 6 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. 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

25 samples harvested: 17 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 0 violated, 13 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
2ran · our draft was wrong
1ran; the contract check could not run
13ran
8unverified

Licence: 6 of the 25 samples are 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 5 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. 3 samples whose link to this paper records no repository are listed under one of this paper's own repositories, because identical code was harvested from it for another paper. 1 sample is listed last, in a group without a repository. “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.

Zzh-tju/CIoU community (archive-listed) 2 samples, 0 ran · 2 unverified
ciou in 11 papers layers/modules/multibox_loss.py unverified GPL-3.0 (copyleft) · pointer only · 3af5f4c25470e411 · report
diou in 10 papers layers/modules/multibox_loss.py unverified GPL-3.0 (copyleft) · pointer only · 7faff7636d39a255 · report
Zzh-tju/ultralytics-YOLOv3-Cluster-NMS community (archive-listed) 3 samples, 2 ran (1 instrument-failed) · 1 unverified
floatn utils/utils.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · honoured contract fingerprinted licence of this copy not recorded · ed702a199df9d0db · report fixture: signature x:float/0/float, n:int/0/int · returned float · level recorded 2026-09-22
load_classes in 13 papers utils/utils.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong licence of this copy not recorded · fa99a26b6ba8f205 · report fixture: signature path:str/0/str · returned list · level recorded 2026-09-22
labels_to_class_weights utils/utils.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own unverified licence of this copy not recorded · 25f32f40bc0cba2f · report
grifon-239/diploma community (archive-listed) 15 samples, 11 ran (0 instrument-failed) · 4 unverified
block in 17 papers common/backbones/efficientnet.py ran MIT (permissive) · 1f6b117f42a0ded5 · report fixture: signature inputs:KerasTensor/0/float, activation_fn:callable/0/?, drop_rate:float/0/float, name:str/0/str, filters_in:int/0/int, filters_out:int/0/int, kernel_size:int/0/int, strides:int/0/int, expand_ratio:int/0/int, se_ratio:float/0/float, id_skip:bool/0/bool · returned KerasTensor · level recorded 2026-09-24
box_diou yolo2/loss.py ran MIT (permissive) · f1144ff6c0ba5dcd · report fixture: signature b_true:EagerTensor/5/float, b_pred:EagerTensor/5/float, use_ciou:bool/0/bool · returned EagerTensor · level recorded 2026-09-24
box_giou yolo2/loss.py ran MIT (permissive) · ae7bb59e3e00b67f · report fixture: signature b_true:EagerTensor/5/float, b_pred:EagerTensor/5/float · returned EagerTensor · level recorded 2026-09-24
box_iou in 34 papers yolo3/loss.py ran MIT (permissive) · a432a967aa4de172 · report fixture: signature b1:EagerTensor/3/float, b2:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-24
channel_shuffle in 35 papers
census: 3 implementations from 7 papers, 2 distinct outputs on one shared input
common/backbones/shufflenet.py ran fingerprinted MIT (permissive) · 287a2f6bfef9fb01 · report fixture: signature x:EagerTensor/4/float, groups:int/0/int · returned EagerTensor · level recorded 2026-09-24
channel_shuffle in 35 papers
census: 3 implementations from 7 papers, 2 distinct outputs on one shared input
common/backbones/shufflenet_v2.py ran fingerprinted MIT (permissive) · e73a09a558400c49 · report fixture: signature x:EagerTensor/4/float · returned EagerTensor · level recorded 2026-09-24
correct_pad in 6 papers common/backbones/efficientnet.py ran MIT (permissive) · 372c139f6aad1ede · report fixture: signature backend:MockBackend/0/?, inputs:Tensor/4/float, kernel_size:int/0/int · returned tuple · level recorded 2026-09-24
relu in 58 papers
census: 8 implementations from 11 papers, 4 distinct outputs across 2 buckets, one shared input per bucket
common/backbones/mobilenet_v3.py ran fingerprinted MIT (permissive) · d304c126a9501818 · report fixture: signature x:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-24
sigmoid_focal_loss in 122 papers
census: 3 implementations from 9 papers, 2 distinct outputs across 2 buckets, one shared input per bucket
yolo3/loss.py ran MIT (permissive) · 119b2c846dc6f0bd · report fixture: signature y_true:EagerTensor/3/float, y_pred:EagerTensor/3/float, gamma:float/0/float, alpha:float/0/float · returned EagerTensor · level recorded 2026-09-24
softmax_focal_loss yolo3/loss.py ran MIT (permissive) · a68a7dc12ee68dda · report fixture: signature y_true:EagerTensor/3/float, y_pred:EagerTensor/3/float, gamma:float/0/float, alpha:float/0/float · returned EagerTensor · level recorded 2026-09-24
swish in 258 papers
census: 14 implementations from 37 papers, 2 distinct outputs on one shared input
common/backbones/efficientnet.py ran fingerprinted MIT (permissive) · d0b798e039050954 · report fixture: signature x:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-24
box_iou in 34 papers yolo2/loss.py unverified MIT (permissive) · 7ac8a3042b335d7e · report
channel_split common/backbones/shufflenet_v2.py unverified MIT (permissive) · 9e94788335c24fb8 · report
fire_module common/backbones/squeezenet.py unverified MIT (permissive) · af81841b8f314e60 · report
shuffle_unit in 5 papers common/backbones/shufflenet_v2.py unverified MIT (permissive) · 6e40e2cdf90c6857 · report
lilanxiao/Rotated_IoU community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
box2corners_th oriented_iou_loss.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · e86bd8530459c52b · report fixture: signature box:Tensor/3/float · returned Tensor · level recorded 2026-09-22
symoon94/YOLO-keras community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
yolo_correct_boxes common/yolo_postprocess_np.py ran MIT (permissive) · b4022b37b8e8571a · report fixture: signature predictions:ndarray/3/float, img_shape:tuple/1/int, model_image_size:tuple/1/int · returned ndarray · level recorded 2026-09-24
yolo_handle_predictions common/yolo_postprocess_np.py ran MIT (permissive) · 04f922be59ea74eb · report fixture: signature predictions:ndarray/3/float, max_boxes:int/0/int, confidence:float/0/float, iou_threshold:float/0/float · returned tuple · level recorded 2026-09-24
yolo_head common/yolo_postprocess_np.py unverified MIT (permissive) · 3ef2976bd580516f · report
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
unique_config_sections in 6 papers repository not located ran · our draft was wrong licence of this copy not recorded · 3b40b5666c482d42 · report fixture: signature config_file:str/0/str · returned StringIO · level recorded 2026-09-22

Tasks

Object Detectionobject-detectionregression

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: DIoU-NMS

1x1 ConvolutionConvolutionDIoU-NMSNon Maximum SuppressionSSD

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