# 2nd Place Solution to Instance Segmentation of IJCAI 3D AI Challenge 2020

Source: [2nd Place Solution to Instance Segmentation of IJCAI 3D AI Challenge 2020](<https://www.sota2.com/research/paper/68fa68881e209131cea1cbe5>)

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

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

Authors: Kai Jiang, Xiangyue Liu, Zheng Ju, Xiang Luo (1)\_\_INSTITUTION\_4\_\_ LinkDoc Technology, Beijing, China, (2) School of Software, Beihang University, Beijing, China, (3) Huaxin consulting Co., Ltd, Hangzhou, China)

Published: 2020-10-21T12:53:01.000Z

## Abstract

Compared with MS-COCO, the dataset for the competition has a larger proportion of large objects which area is greater than 96x96 pixels. As getting fine boundaries is vitally important for large object segmentation, Mask R-CNN with PointRend is selected as the base segmentation framework to output high-quality object boundaries. Besides, a better engine that integrates ResNeSt, FPN and DCNv2, and a range of effective tricks that including multi-scale training and test time augmentation are applied to improve segmentation performance. Our best performance is an ensemble of four models (three PointRend-based models and SOLOv2), which won the 2nd place in IJCAI-PRICAI 3D AI Challenge 2020: Instance Segmentation.

## 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/2010.10957>)

[PDF](<https://arxiv.org/pdf/2010.10957.pdf>)