English

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

Computer Vision and Pattern Recognition 2023-07-24 v1

Abstract

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 .

Keywords

Cite

@article{arxiv.2307.11748,
  title  = {BandRe: Rethinking Band-Pass Filters for Scale-Wise Object Detection Evaluation},
  author = {Yosuke Shinya},
  journal= {arXiv preprint arXiv:2307.11748},
  year   = {2023}
}

Comments

Honorable Mention Solution Award in Small Object Detection Challenge for Spotting Birds, International Conference on Machine Vision Applications (MVA) 2023

R2 v1 2026-06-28T11:37:12.586Z