Papers › CityPersons: A Diverse Dataset for Pedestrian Detection

CityPersons: A Diverse Dataset for Pedestrian Detection

19 Feb 2017CVPR 2017 7arXiv:1702.05693archive 2025-07-28

Shanshan Zhang, Rodrigo Benenson, Bernt Schiele

Convnets have enabled significant progress in pedestrian detection recently, but there are still open questions regarding suitable architectures and training data. We revisit CNN design and point out key adaptations, enabling plain FasterRCNN to obtain state-of-the-art results on the Caltech dataset. To achieve further improvement from more and better data, we introduce CityPersons, a new set of person annotations on top of the Cityscapes dataset. The diversity of CityPersons allows us for the first time to train one single CNN model that generalizes well over multiple benchmarks. Moreover, with additional training with CityPersons, we obtain top results using FasterRCNN on Caltech, improving especially for more difficult cases (heavy occlusion and small scale) and providing higher localization quality.

PaperPDFConference PDFCode

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

Code

aibeedetect/bfjdet mentioned on GitHubpytorchMIT report
hnuzhy/bpjdet mentioned on GitHubpytorchGPL-3.0 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

DiversityPedestrian Detection

Datasets

Introduced by this paper, per the archive.

CityPersons

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Pedestrian Detection Caltech Zhang et al. * Reasonable Miss Rate 5.1 #14 of 33 Archive leaderboard report
Pedestrian Detection Caltech Zhang et al. Reasonable Miss Rate 5.8 #16 of 33 Archive leaderboard report
Pedestrian Detection CityPersons FRCNN+Seg Large MR^-2 8.0 #19 of 22 Archive leaderboard report
Pedestrian Detection CityPersons FRCNN+Seg Medium MR^-2 6.7 #19 of 22 Archive leaderboard report
Pedestrian Detection CityPersons FRCNN+Seg Reasonable MR^-2 14.8 #19 of 22 Archive leaderboard report
Pedestrian Detection CityPersons FRCNN+Seg Small MR^-2 22.6 #19 of 22 Archive leaderboard report
Pedestrian Detection CityPersons FRCNN Large MR^-2 7.9 #20 of 22 Archive leaderboard report
Pedestrian Detection CityPersons FRCNN Medium MR^-2 7.2 #20 of 22 Archive leaderboard report
Pedestrian Detection CityPersons FRCNN Reasonable MR^-2 15.4 #20 of 22 Archive leaderboard report
Pedestrian Detection CityPersons FRCNN Small MR^-2 25.6 #20 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