A Solution to Product detection in Densely Packed Scenes
Published in
arXiv.org(2020)External Links:
TL
TL;DR
This work proposed a random crop strategy to ensure both the sampling rate and input scale is relatively sufficient as a contrast to the regular random crop and adopted some of trick and optimized the hyper-parameters.
Abstract
This work is a solution to densely packed scenes dataset SKU-110k. Our work is modified from cascade R-CNN. To solve the problem, we proposed a random crop strategy to ensure both the sampling rate and input scale is relatively sufficient as a contrast to the regular random crop. And we adopted some of trick and optimized the hyper-parameters. To grasp the essential feature of the densely packed scenes, we analysis the stages of a detector and investigate the bottleneck which limits the performance. As a result, our method obtains 58.7 mAP on test set of SKU-110k.
References10 items
1
EfficientDet: Scalable and Efficient Object Detection
2
MMDetection: Open MMLab Detection Toolbox and Benchmark
3
Precise Detection in Densely Packed Scenes
4
Cascade R-CNN: Delving Into High Quality Object Detection
5