Papers › Training-Time-Friendly Network for Real-Time Object Detection

Training-Time-Friendly Network for Real-Time Object Detection

2 Sep 2019arXiv:1909.00700archive 2025-07-28

Zili Liu, Tu Zheng, Guodong Xu, Zheng Yang, Haifeng Liu, Deng Cai

Modern object detectors can rarely achieve short training time, fast inference speed, and high accuracy at the same time. To strike a balance among them, we propose the Training-Time-Friendly Network (TTFNet). In this work, we start with light-head, single-stage, and anchor-free designs, which enable fast inference speed. Then, we focus on shortening training time. We notice that encoding more training samples from annotated boxes plays a similar role as increasing batch size, which helps enlarge the learning rate and accelerate the training process. To this end, we introduce a novel approach using Gaussian kernels to encode training samples. Besides, we design the initiative sample weights for better information utilization. Experiments on MS COCO show that our TTFNet has great advantages in balancing training time, inference speed, and accuracy. It has reduced training time by more than seven times compared to previous real-time detectors while maintaining state-of-the-art performances. In addition, our super-fast version of TTFNet-18 and TTFNet-53 can outperform SSD300 and YOLOv3 by less than one-tenth of their training time, respectively. The code has been made available at https://github.com/ZJULearning/ttfnet.

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 (ZJULearning/ttfnet) was not harvested; the 8 samples below come from 1 community repository.

Syntology 8 code samples harvested from 1 repository linked to this paper: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 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): 8 samples from 1 repository, 5 ran (4 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

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

ZJULearning/ttfnet officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: not harvested report
593903762/ttf mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
XinYangDong/ttfnet-master2 mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
oulin1031esti/detect mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
ximilar-com/xcenternet mentioned on GitHubtfMITSyntology: 8 samples, 5 ran (1 instrument-failed) · 3 unverified 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

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

8 samples harvested: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 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; the contract check could not run
4ran
3unverified

Licence: 1 of the 8 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 ximilar-com/xcenternet. “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.

ximilar-com/xcenternet community (archive-listed) 8 samples, 5 ran (1 instrument-failed) · 3 unverified
draw_umich_gaussian in 6 papers xcenternet/model/encoder.py ran MIT (permissive) · 97ec0f498e1be4e1 · report fixture: signature heatmap:ndarray/2/float, center:tuple/1/int, radius:int/0/int, k:int/0/int · returned ndarray · level recorded 2026-09-24
gaussian2D in 13 papers xcenternet/model/encoder.py ran MIT (permissive) · c171c4b57b660e23 · report fixture: signature shape:tuple/1/int, sigma_x:float/0/float, sigma_y:float/0/float · returned ndarray · level recorded 2026-09-24
gaussian_radius in 25 papers xcenternet/model/encoder.py ran; the contract check could not run (RAISES) MIT (permissive) here; the stored copy is pointer only · f2a33236566ea043 · report fixture: signature det_size:tuple/1/int, min_overlap:float/0/float · returned float64 · level recorded 2026-09-24
heatmap_focal_loss xcenternet/model/loss.py ran MIT (permissive) · d81ea661f423acca · report fixture: signature outputs:dict/0/?, training_data:NoneType/0/?, predictions:list/1/EagerTensor · returned SymbolicTensor · level recorded 2026-09-24
nms in 65 papers xcenternet/model/decoder.py ran fingerprinted MIT (permissive) · bebeea9a1d22ce22 · report fixture: signature heat:EagerTensor/4/float, kernel:int/0/int · returned EagerTensor · level recorded 2026-09-24
offset_l1_loss xcenternet/model/loss.py unverified MIT (permissive) · e14793d929c62e92 · report
size_l1_loss xcenternet/model/loss.py unverified MIT (permissive) · 6f7345c38f60f030 · report
topk in 19 papers xcenternet/model/decoder.py unverified MIT (permissive) · 116fc2a94a061185 · report

Tasks

ObjectObject DetectionReal-Time Object Detectionobject-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