A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentation
[article]
2020
arXiv
pre-print
Most existing object instance detection and segmentation models only work well on fairly balanced benchmarks where per-category training sample numbers are comparable, such as COCO. They tend to suffer performance drop on realistic datasets that are usually long-tailed. This work aims to study and address such open challenges. Specifically, we systematically investigate performance drop of the state-of-the-art two-stage instance segmentation model Mask R-CNN on the recent long-tail LVIS
arXiv:2007.11978v5
fatcat:gigp7bmq3rcfjport7b67xtc4y