paper-with-me

Papers

Strong Instance Segmentation Pipeline for MMSports Challenge

2022-09-28 · Bo Yan, Fengliang Qi, Zhuang Li, Yadong Li, Hongbin Wang

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.

📄 PDF Abstract BibTeX arXiv:2209.13899

Code (2)

yjingyu/instanc_segmentation_pro 공식 구현 pytorch
deepsportradar/instance-segmentation-challenge

Tasks

Data AugmentationInstance SegmentationSegmentationSemantic Segmentation

Methods 이 논문이 사용한 방법론

Copy-Paste 설명 없음

Similar Papers 제목 키워드 기반

Instance Segmentation under Occlusions via Location-aware Copy-Paste Data Augmentation

2023-10-27 · Son Nguyen, Mikel Lainsa, Hung Dao, Daeyoung Kim 외

Occlusion is a long-standing problem in computer vision, particularly in instance segmentation. ACM MMSports 2023 DeepSportRadar has introduced a dataset that focuses on segmenting human subjects within a basketball cont…

Data AugmentationInstance SegmentationSegmentationSemantic Segmentation

Towards Robust Part-aware Instance Segmentation for Industrial Bin Picking

2022-03-05 · Yidan Feng, Biqi Yang, Xianzhi Li, Chi-Wing Fu 외

Industrial bin picking is a challenging task that requires accurate and robust segmentation of individual object instances. Particularly, industrial objects can have irregular shapes, that is, thin and concave, whereas i…

Instance SegmentationSegmentationSemantic Segmentation

Tracking Instances as Queries

2021-06-22 · Shusheng Yang, Yuxin Fang, Xinggang Wang, Yu Li 외

Recently, query based deep networks catch lots of attention owing to their end-to-end pipeline and competitive results on several fundamental computer vision tasks, such as object detection, semantic segmentation, and in…

Instance Segmentationobject-detectionObject DetectionSegmentation+2

DeepSportradar-v1: Computer Vision Dataset for Sports Understanding with High Quality Annotations

2022-08-17 · Gabriel Van Zandycke, Vladimir Somers, Maxime Istasse, Carlo Del Don 외

With the recent development of Deep Learning applied to Computer Vision, sport video understanding has gained a lot of attention, providing much richer information for both sport consumers and leagues. This paper introdu…

Camera CalibrationInstance SegmentationSemantic SegmentationSports Understanding+1

STC: Spatio-Temporal Contrastive Learning for Video Instance Segmentation

2022-02-08 · Zhengkai Jiang, Zhangxuan Gu, Jinlong Peng, Hang Zhou 외

Video Instance Segmentation (VIS) is a task that simultaneously requires classification, segmentation, and instance association in a video. Recent VIS approaches rely on sophisticated pipelines to achieve this goal, incl…

Contrastive LearningInstance SegmentationSegmentationSemantic Segmentation+1