Dynamic boxes fusion strategy in object detection
This work addresses parasitic egg detection in microscopic images for medical diagnostics, but it is incremental as it builds on existing ensemble methods.
The paper tackled object detection in microscopic images with variable magnifications and blurry boundaries by proposing training strategies and a new box selection and fusion method for multi-model ensemble, achieving 1st place in a challenge with mIoU 95.28% and mF1Score 99.62%.
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.