VisDrone-ReID: A Unified Multi-Category Object Re-Identification Benchmark

Object re-identification (Re-ID) benchmarks remain predominantly confined to single-category evaluations, limiting the development of unified systems capable of operating across diverse object types. This paper presents VisDrone-ReID, a unified multi-category Re-ID benchmark derived from the VisDrone2019-MOT dataset through a principled conversion pipeline. The pipeline resolves structural incompatibilities between multi-object tracking annotations and Re-ID evaluation requirements, addressing sequence-scoped identity collision, temporal redundancy, and the absence of a principled identity-level train/test split. The resulting benchmark comprises 9,516 identities and 150,016 images across ten object categories - pedestrian, people, bicycle, car, van, truck, tricycle, awning-tricycle, bus, and motor, sourced from 80 unmanned aerial vehicle (UAV) sequences captured across urban environments. A leave-one-out (LOO) evaluation protocol is adopted to provide a comprehensive assessment. Baseline experiments across four representative Re-ID models spanning CNN and transformer architectures establish the first systematic performance reference on this benchmark. Results reveal a consistent Rank-1 to mAP gap across all models, suggesting that VisDrone-ReID presents a genuine retrieval challenge beyond nearest-neighbour matching. Per-category analysis identifies pedestrian as the most challenging category and reveals that vision-language pretraining provides a measurable advantage on semantically distinctive categories. VisDrone-ReID provides a consistent platform for studying multi-category object re-identification under the scale variation, viewpoint challenges, and category diversity characteristic of real-world surveillance scenarios.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-16
DOI
https://doi.org/10.48550/arxiv.2611.20372
Primary Topic
Video Surveillance and Tracking Methods
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

VisDrone-ReID: A Unified Multi-Category Object Re-Identification Benchmark

Nathanael L. Baisa, Asmau Lawal Bilbis, Amudhavel Jayavel
arXiv (Cornell University)
Video Surveillance and Tracking Methods
preprint

VisDrone-ReID: A Unified Multi-Category Object Re-Identification Benchmark

Nathanael L. Baisa, Asmau Lawal Bilbis, Amudhavel Jayavel
preprint en

Abstract

Object re-identification (Re-ID) benchmarks remain predominantly confined to single-category evaluations, limiting the development of unified systems capable of operating across diverse object types. This paper presents VisDrone-ReID, a unified multi-category Re-ID benchmark derived from the VisDrone2019-MOT dataset through a principled conversion pipeline. The pipeline resolves structural incompatibilities between multi-object tracking annotations and Re-ID evaluation requirements, addressing sequence-scoped identity collision, temporal redundancy, and the absence of a principled identity-level train/test split. The resulting benchmark comprises 9,516 identities and 150,016 images across ten object categories - pedestrian, people, bicycle, car, van, truck, tricycle, awning-tricycle, bus, and motor, sourced from 80 unmanned aerial vehicle (UAV) sequences captured across urban environments. A leave-one-out (LOO) evaluation protocol is adopted to provide a comprehensive assessment. Baseline experiments across four representative Re-ID models spanning CNN and transformer architectures establish the first systematic performance reference on this benchmark. Results reveal a consistent Rank-1 to mAP gap across all models, suggesting that VisDrone-ReID presents a genuine retrieval challenge beyond nearest-neighbour matching. Per-category analysis identifies pedestrian as the most challenging category and reveals that vision-language pretraining provides a measurable advantage on semantically distinctive categories. VisDrone-ReID provides a consistent platform for studying multi-category object re-identification under the scale variation, viewpoint challenges, and category diversity characteristic of real-world surveillance scenarios.

arXiv (Cornell University)
Video Surveillance and Tracking Methods
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon