# Joint COCO and Mapillary Workshop at ICCV 2019: COCO Instance Segmentation Challenge Track

Source: [Joint COCO and Mapillary Workshop at ICCV 2019: COCO Instance Segmentation Challenge Track](<https://www.sota2.com/research/paper/68fa686b1e209131cea1c080>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:04:44.961Z

Authors: Zeming Li, Yuchen Ma, Yukang Chen, Xiangyu Zhang, Jian Sun

Published: 2020-10-06T04:49:37.000Z

## Abstract

In this report, we present our object detection/instance segmentation system, MegDetV2, which works in a two-pass fashion, first to detect instances then to obtain segmentation. Our baseline detector is mainly built on a new designed RPN, called RPN++. On the COCO-2019 detection/instance-segmentation test-dev dataset, our system achieves 61.0/53.1 mAP, which surpassed our 2018 winning results by 5.0/4.2 respectively. We achieve the best results in COCO Challenge 2019 and 2020.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2010.02475>)

[PDF](<https://arxiv.org/pdf/2010.02475.pdf>)