Strong Instance Segmentation Pipeline for MMSports Challenge

TL;DR

This paper presents a robust instance segmentation pipeline for sports images, combining data augmentation, a strong hybrid model, and SWA training to effectively segment players in challenging basketball court scenarios.

Contribution

It introduces a comprehensive segmentation pipeline with novel data augmentation, a hybrid model with MaskIoU head, and SWA training, tailored for sports imagery with occlusions and limited data.

Findings

Achieved 0.768 AP on challenge set

Effective handling of occlusions and limited data

Demonstrated competitive performance in MMSports challenge

Abstract

The goal of ACM MMSports2022 DeepSportRadar Instance Segmentation Challenge is to tackle the segmentation of individual humans including players, coaches and referees on a basketball court. And the main characteristics of this challenge are there is a high level of occlusions between players and the amount of data is quite limited. In order to address these problems, we designed a strong instance segmentation pipeline. Firstly, we employed a proper data augmentation strategy for this task mainly including photometric distortion transform and copy-paste strategy, which can generate more image instances with a wider distribution. Secondly, we employed a strong segmentation model, Hybrid Task Cascade based detector on the Swin-Base based CBNetV2 backbone, and we add MaskIoU head to HTCMaskHead that can simply and effectively improve the performance of instance segmentation. Finally, the SWA training strategy was applied to improve the performance further. Experimental results demonstrate the proposed pipeline can achieve a competitive result on the DeepSportRadar challenge, with 0.768AP@0.50:0.95 on the challenge set. Source code is available at https://github.com/YJingyu/Instanc_Segmentation_Pro.