Papers › NOH-NMS: Improving Pedestrian Detection by Nearby Objects Hallucination

NOH-NMS: Improving Pedestrian Detection by Nearby Objects Hallucination

27 Jul 2020arXiv:2007.13376archive 2025-07-28

Penghao Zhou, Chong Zhou, Pai Peng, Junlong Du, Xing Sun, Xiaowei Guo, Feiyue Huang

Greedy-NMS inherently raises a dilemma, where a lower NMS threshold will potentially lead to a lower recall rate and a higher threshold introduces more false positives. This problem is more severe in pedestrian detection because the instance density varies more intensively. However, previous works on NMS don't consider or vaguely consider the factor of the existent of nearby pedestrians. Thus, we propose Nearby Objects Hallucinator (NOH), which pinpoints the objects nearby each proposal with a Gaussian distribution, together with NOH-NMS, which dynamically eases the suppression for the space that might contain other objects with a high likelihood. Compared to Greedy-NMS, our method, as the state-of-the-art, improves by 3.9% AP, 5.1% Recall, and 0.8% MR⁻² on CrowdHuman to 89.0% AP and 92.9% Recall, and 43.9% MR⁻² respectively.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

TencentYoutuResearch/PedestrianDetection-NohNMS officialmentioned on GitHubpytorch 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

HallucinationObject DetectionPedestrian Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection CrowdHuman (full body) NOH-NMS AP 89.0 #13 of 19 Archive leaderboard report
Object Detection CrowdHuman (full body) NOH-NMS mMR 43.9 #13 of 19 Archive leaderboard report
Pedestrian Detection CityPersons NOH-NMS Bare MR^-2 6.6 #13 of 22 Archive leaderboard report
Pedestrian Detection CityPersons NOH-NMS Heavy MR^-2 53.0 #13 of 22 Archive leaderboard report
Pedestrian Detection CityPersons NOH-NMS Partial MR^-2 11.2 #13 of 22 Archive leaderboard report
Pedestrian Detection CityPersons NOH-NMS Reasonable MR^-2 10.8 #13 of 22 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