Papers › A Normalized Gaussian Wasserstein Distance for Tiny Object Detection

A Normalized Gaussian Wasserstein Distance for Tiny Object Detection

26 Oct 2021arXiv:2110.13389archive 2025-07-28

Jinwang Wang, Chang Xu, Wen Yang, Lei Yu

Detecting tiny objects is a very challenging problem since a tiny object only contains a few pixels in size. We demonstrate that state-of-the-art detectors do not produce satisfactory results on tiny objects due to the lack of appearance information. Our key observation is that Intersection over Union (IoU) based metrics such as IoU itself and its extensions are very sensitive to the location deviation of the tiny objects, and drastically deteriorate the detection performance when used in anchor-based detectors. To alleviate this, we propose a new evaluation metric using Wasserstein distance for tiny object detection. Specifically, we first model the bounding boxes as 2D Gaussian distributions and then propose a new metric dubbed Normalized Wasserstein Distance (NWD) to compute the similarity between them by their corresponding Gaussian distributions. The proposed NWD metric can be easily embedded into the assignment, non-maximum suppression, and loss function of any anchor-based detector to replace the commonly used IoU metric. We evaluate our metric on a new dataset for tiny object detection (AI-TOD) in which the average object size is much smaller than existing object detection datasets. Extensive experiments show that, when equipped with NWD metric, our approach yields performance that is 6.7 AP points higher than a standard fine-tuning baseline, and 6.0 AP points higher than state-of-the-art competitors. Codes are available at: https://github.com/jwwangchn/NWD.

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

Syntology 2 code samples harvested from 1 repository linked to this paper: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 2 samples from 1 repository, 2 ran (2 with no instrument failure; 0 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 on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

jwwangchn/NWD officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
bhyun-kim/NWD mentioned on GitHubMITSyntology: not harvested report
pierlj/pycocosiou mentioned on GitHubSyntology: 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.

Code Syntology ran Syntology

2 samples harvested: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 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.

2ran

Licence: 2 of the 2 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 jwwangchn/NWD. “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.

jwwangchn/NWD official repository 2 samples, 2 ran (0 instrument-failed) · 0 unverified
get_final_results in 23 papers .dev_scripts/gather_models.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · 2268355e37eebb82 · report fixture: signature log_json_path:str/0/str, epoch:int/0/int, results_lut:list/1/str · returned dict · level recorded 2026-09-24
process_checkpoint in 87 papers .dev_scripts/gather_models.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · ae35528c6bd4bd1c · report fixture: signature in_file:str/0/str, out_file:str/0/str · returned str · level recorded 2026-09-24

Tasks

ObjectObject DetectionSmall Object Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection AI-TOD DetectoRS + NWD (ResNet-50-FPN) AP 20.8 #3 of 7 Archive leaderboard report
Object Detection AI-TOD DetectoRS + NWD (ResNet-50-FPN) AP50 49.3 #3 of 7 Archive leaderboard report
Object Detection AI-TOD DetectoRS + NWD (ResNet-50-FPN) AP75 14.3 #3 of 7 Archive leaderboard report
Object Detection AI-TOD DetectoRS + NWD (ResNet-50-FPN) APm 38.3 #3 of 7 Archive leaderboard report
Object Detection AI-TOD DetectoRS + NWD (ResNet-50-FPN) APs 29.6 #3 of 7 Archive leaderboard report
Object Detection AI-TOD DetectoRS + NWD (ResNet-50-FPN) APt 19.7 #3 of 7 Archive leaderboard report
Object Detection AI-TOD DetectoRS + NWD (ResNet-50-FPN) APvt 6.4 #3 of 7 Archive leaderboard report
Object Detection VisDrone-DET2019 Cascade R-CNN + NWD AP50 40.3 #4 of 5 Archive leaderboard report
Object Detection VisDrone-DET2019 Cascade R-CNN + NWD APs 22.2 #4 of 5 Archive leaderboard report
Object Detection VisDrone-DET2019 Cascade R-CNN + NWD APt 11.1 #4 of 5 Archive leaderboard report
Object Detection VisDrone-DET2019 Cascade R-CNN + NWD APvt 2.9 #4 of 5 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.

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