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

10/21/2020
by   Kai Jiang, et al.
0

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.

READ FULL TEXT

page 2

page 3

09/10/2020

Towards Fine-grained Large Object Segmentation 1st Place Solution to 3D AI Challenge 2020 – Instance Segmentation Track

This technical report introduces our solutions of Team 'FineGrainedSeg' ...
10/06/2020

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

In this report, we present our object detection/instance segmentation sy...
04/12/2021

Look Closer to Segment Better: Boundary Patch Refinement for Instance Segmentation

Tremendous efforts have been made on instance segmentation but the mask ...
04/17/2021

RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features

The two-stage methods for instance segmentation, e.g. Mask R-CNN, have a...
03/05/2018

Path Aggregation Network for Instance Segmentation

The way that information propagates in neural networks is of great impor...
01/14/2021

How Shift Equivariance Impacts Metric Learning for Instance Segmentation

Metric learning has received conflicting assessments concerning its suit...
10/15/2020

Pick-Place With Uncertain Object Instance Segmentation and Shape Completion

In this paper we consider joint perception and control of a pick-place s...