Papers › Bag of Freebies for Training Object Detection Neural Networks

Bag of Freebies for Training Object Detection Neural Networks

11 Feb 2019arXiv:1902.04103archive 2025-07-28

Zhi Zhang, Tong He, Hang Zhang, Zhongyue Zhang, Junyuan Xie, Mu Li

Training heuristics greatly improve various image classification model accuracies. Object detection models, however, have more complex neural network structures and optimization targets. The training strategies and pipelines dramatically vary among different models. In this works, we explore training tweaks that apply to various models including Faster R-CNN and YOLOv3. These tweaks do not change the model architectures, therefore, the inference costs remain the same. Our empirical results demonstrate that, however, these freebies can improve up to 5% absolute precision compared to state-of-the-art baselines.

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 (dmlc/gluon-cv) was not harvested; the 18 samples below come from 1 community repository.

Syntology 18 code samples harvested from 1 repository linked to this paper: 15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 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, 15 ran (14 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 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

dmlc/gluon-cv officialmentioned in papertfApache-2.0Syntology: not harvested report
lingtengqiu/Yolo_Nano mentioned on GitHubpytorchSyntology: not harvested report
wizyoung/YOLOv3_TensorFlow mentioned on GitHubtfMITSyntology: 18 samples, 15 ran (1 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

18 samples harvested: 15 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 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 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; the contract check could not run
14ran
3unverified

Licence: 0 of the 18 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 wizyoung/YOLOv3_TensorFlow. “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.

wizyoung/YOLOv3_TensorFlow community (archive-listed) 18 samples, 15 ran (1 instrument-failed) · 3 unverified
avg_iou get_kmeans.py ran fingerprinted MIT (permissive) · 34e841aabf1b96f9 · report fixture: signature boxes:ndarray/2/float, clusters:ndarray/2/float · returned float32 · level recorded 2026-09-25
bbox_crop utils/data_aug.py ran MIT (permissive) · 00fa5fa35fceddc1 · report fixture: signature bbox:ndarray/2/float, crop_box:tuple/1/int, allow_outside_center:bool/0/bool · returned ndarray · level recorded 2026-09-24
bbox_iou in 21 papers utils/data_aug.py ran fingerprinted MIT (permissive) · bd08a00ded7caa44 · report fixture: signature bbox_a:ndarray/2/float, bbox_b:ndarray/2/float, offset:int/0/int · returned ndarray · level recorded 2026-09-24
calc_iou in 17 papers utils/eval_utils.py ran fingerprinted MIT (permissive) · 9db9b9965e68c8ad · report fixture: signature pred_boxes:ndarray/2/float, true_boxes:ndarray/2/float · returned ndarray · level recorded 2026-09-24
cpu_nms utils/nms_utils.py ran MIT (permissive) · f969b2977a72cc55 · report fixture: signature boxes:ndarray/3/float, scores:ndarray/3/float, num_classes:int/0/int, max_boxes:int/0/int, score_thresh:float/0/float, iou_thresh:float/0/float · returned tuple · level recorded 2026-09-24
gpu_nms utils/nms_utils.py ran MIT (permissive) · 5f0874e5158a0875 · report fixture: signature boxes:EagerTensor/3/float, scores:EagerTensor/3/float, num_classes:int/0/int, max_boxes:int/0/int, score_thresh:float/0/float, nms_thresh:float/0/float · returned tuple · level recorded 2026-09-24
iou in 97 papers
census: 5 implementations from 7 papers, 5 distinct outputs across 5 buckets, one shared input per bucket
get_kmeans.py ran MIT (permissive) · 95c4cba76be0a2a1 · report fixture: signature box:tuple/1/float, clusters:ndarray/2/float · returned ndarray · level recorded 2026-09-24
make_summary in 6 papers utils/misc_utils.py ran MIT (permissive) · ff97bfe78626bb8e · report fixture: signature name:str/0/str, val:float/0/float · returned Summary · level recorded 2026-09-24
mix_up utils/data_aug.py ran MIT (permissive) · b3ec10e70300afb7 · report fixture: signature img1:ndarray/3/int, img2:ndarray/3/int, bbox1:ndarray/2/float, bbox2:ndarray/2/float · returned tuple · level recorded 2026-09-24
parse_anchors utils/misc_utils.py ran MIT (permissive) · 44e65a34fe58f184 · report fixture: signature anchor_path:str/0/str · returned ndarray · level recorded 2026-09-24
parse_line in 17 papers utils/data_utils.py ran MIT (permissive) · 7a494e675e71f1f9 · report fixture: signature line:str/0/str · returned tuple · level recorded 2026-09-24
process_box utils/data_utils.py ran MIT (permissive) · fc500933be7ea183 · report fixture: signature boxes:ndarray/2/float, labels:ndarray/1/int, img_size:tuple/1/int, class_num:int/0/int, anchors:ndarray/2/float · returned tuple · level recorded 2026-09-24
py_nms utils/nms_utils.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · 647b8865c23ab104 · report fixture: signature boxes:ndarray/2/float, scores:ndarray/1/float, max_boxes:int/0/int, iou_thresh:float/0/float · returned list · level recorded 2026-09-22
read_class_names in 6 papers utils/misc_utils.py ran MIT (permissive) · 9f9d523c4fc9a5d5 · report fixture: signature class_name_path:str/0/str · returned dict · level recorded 2026-09-24
translate_boxes get_kmeans.py ran fingerprinted MIT (permissive) · b9b52f6b2d452deb · report fixture: signature boxes:ndarray/2/float · returned ndarray · level recorded 2026-09-24
evaluate_on_gpu utils/eval_utils.py unverified MIT (permissive) · a21ccdee37daac79 · report
parse_data in 16 papers utils/data_utils.py unverified MIT (permissive) · c6da8f222212852c · report
parse_xml misc/parse_voc_xml.py unverified MIT (permissive) · a6fbd5e031368b6e · report

Tasks

General ClassificationImage ClassificationObject Detectionimage-classificationobject-detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationConvolutionGlobal Average PoolingLogistic RegressionResidual ConnectionSoftmaxYOLOv3k-Means Clustering

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