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 .
@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