Papers › LLA: Loss-aware Label Assignment for Dense Pedestrian Detection

LLA: Loss-aware Label Assignment for Dense Pedestrian Detection

12 Jan 2021arXiv:2101.04307archive 2025-07-28

Zheng Ge, JianFeng Wang, Xin Huang, Songtao Liu, Osamu Yoshie

Label assignment has been widely studied in general object detection because of its great impact on detectors' performance. However, none of these works focus on label assignment in dense pedestrian detection. In this paper, we propose a simple yet effective assigning strategy called Loss-aware Label Assignment (LLA) to boost the performance of pedestrian detectors in crowd scenarios. LLA first calculates classification (cls) and regression (reg) losses between each anchor and ground-truth (GT) pair. A joint loss is then defined as the weighted summation of cls and reg losses as the assigning indicator. Finally, anchors with top K minimum joint losses for a certain GT box are assigned as its positive anchors. Anchors that are not assigned to any GT box are considered negative. Loss-aware label assignment is based on an observation that anchors with lower joint loss usually contain richer semantic information and thus can better represent their corresponding GT boxes. Experiments on CrowdHuman and CityPersons show that such a simple label assigning strategy can boost MR by 9.53% and 5.47% on two famous one-stage detectors - RetinaNet and FCOS, respectively, demonstrating the effectiveness of LLA.

PaperPDFCode

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

Code

Megvii-BaseDetection/LLA officialmentioned in papermentioned 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

Object DetectionPedestrian Detectionobject-detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionConvolutionFCOSFPNFocal LossNon Maximum SuppressionRetinaNet

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