Dynamic boxes fusion strategy in object detection

TL;DR

This paper introduces a novel boxes fusion strategy and training techniques for microscopic object detection, achieving state-of-the-art results on the Chula-ParasiteEgg-11 dataset and winning a challenge.

Contribution

It proposes a new box selection and fusion method for multi-model ensemble in microscopic object detection, addressing scale variation and blurriness issues.

Findings

Achieved 1st place in ICIP 2022 Challenge with mIoU 95.28%

Demonstrated significant improvements on Chula-ParasiteEgg-11 dataset

Provided effective training strategies for microscopic image detection

Abstract

Object detection on microscopic scenarios is a popular task. As microscopes always have variable magnifications, the object can vary substantially in scale, which burdens the optimization of detectors. Moreover, different situations of camera focusing bring in the blurry images, which leads to great challenge of distinguishing the boundaries between objects and background. To solve the two issues mentioned above, we provide bags of useful training strategies and extensive experiments on Chula-ParasiteEgg-11 dataset, bring non-negligible results on ICIP 2022 Challenge: Parasitic Egg Detection and Classification in Microscopic Images, further more, we propose a new box selection strategy and an improved boxes fusion method for multi-model ensemble, as a result our method wins 1st place(mIoU 95.28%, mF1Score 99.62%), which is also the state-of-the-art method on Chula-ParasiteEgg-11 dataset.