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

TL;DR

This paper presents a high-performing ensemble method for instance segmentation in the IJCAI 3D AI Challenge 2020, utilizing advanced models and training tricks to improve boundary accuracy on large objects.

Contribution

The authors develop an ensemble of PointRend-based Mask R-CNN models with ResNeSt, FPN, and DCNv2, achieving second place in the challenge.

Findings

Ensemble of four models achieved top performance.

Multi-scale training and test augmentation improved results.

PointRend enhanced boundary quality for large objects.

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.