Papers › BandRe: Rethinking Band-Pass Filters for Scale-Wise Object Detection Evaluation

BandRe: Rethinking Band-Pass Filters for Scale-Wise Object Detection Evaluation

21 Jul 2023arXiv:2307.11748archive 2025-07-28

Yosuke Shinya

Scale-wise evaluation of object detectors is important for real-world applications. However, existing metrics are either coarse or not sufficiently reliable. In this paper, we propose novel scale-wise metrics that strike a balance between fineness and reliability, using a filter bank consisting of triangular and trapezoidal band-pass filters. We conduct experiments with two methods on two datasets and show that the proposed metrics can highlight the differences between the methods and between the datasets. Code is available at https://github.com/shinya7y/UniverseNet .

PaperPDFCode

Code

shinya7y/UniverseNet officialmentioned in paperpytorchApache-2.0 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

Object DetectionReal-Time Object DetectionSmall Object Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Small Object Detection SOD4SB Private Test GFL + Test Time Augmentation AP50 23.7 #2 of 5 Archive leaderboard report
Small Object Detection SOD4SB Public Test GFL + Test Time Augmentation AP50 73.1 #2 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