Guided Sampling Based Feature Aggregation for Video Object Detection

Jun Liang, Haosheng Chen, Y. Yan, Yang Lu, Hanzi Wang
{"title":"Guided Sampling Based Feature Aggregation for Video Object Detection","authors":"Jun Liang, Haosheng Chen, Y. Yan, Yang Lu, Hanzi Wang","doi":"10.1109/ICIP46576.2022.9897210","DOIUrl":null,"url":null,"abstract":"Video object detection is a challenging task due to the presence of appearance deterioration in video frames. Recently, feature aggregation based methods which aggregate context information from object proposals in different frames to improve the performance, have dominated the task. However, much invalid information may be introduced during feature aggregation since frames and proposals are usually selected at random. In this paper, we propose a guided sampling based feature aggregation network (GSFA) to perform more effective feature aggregation. Specifically, we introduce a frame-level sampling module and a proposal-level sampling module to sample informative frames and proposals from a video sequence adaptively. As a result, the proposed GSFA can effectively aggregate context information from the semantically rich frames and proposals to boost the performance. Experimental results on the ImageNet VID dataset show the proposed GSFA achieves the state-of-the-art performance of 84.8% mAP with ResNet-101 and 85.8% mAP with ResNeXt-101.","PeriodicalId":387035,"journal":{"name":"2022 IEEE International Conference on Image Processing (ICIP)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE International Conference on Image Processing (ICIP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICIP46576.2022.9897210","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

Abstract

Video object detection is a challenging task due to the presence of appearance deterioration in video frames. Recently, feature aggregation based methods which aggregate context information from object proposals in different frames to improve the performance, have dominated the task. However, much invalid information may be introduced during feature aggregation since frames and proposals are usually selected at random. In this paper, we propose a guided sampling based feature aggregation network (GSFA) to perform more effective feature aggregation. Specifically, we introduce a frame-level sampling module and a proposal-level sampling module to sample informative frames and proposals from a video sequence adaptively. As a result, the proposed GSFA can effectively aggregate context information from the semantically rich frames and proposals to boost the performance. Experimental results on the ImageNet VID dataset show the proposed GSFA achieves the state-of-the-art performance of 84.8% mAP with ResNet-101 and 85.8% mAP with ResNeXt-101.
基于引导采样的特征聚合视频目标检测
视频目标检测是一项具有挑战性的任务,因为视频帧中存在外观劣化。近年来,基于特征聚合的方法从不同帧的对象建议中聚合上下文信息以提高性能,在该任务中占主导地位。然而,由于帧和提议通常是随机选择的,因此在特征聚合过程中可能会引入许多无效信息。在本文中,我们提出了一种基于引导采样的特征聚合网络(GSFA)来进行更有效的特征聚合。具体来说,我们引入了帧级采样模块和提案级采样模块来自适应地从视频序列中采样信息帧和提案。结果表明,所提出的GSFA能够有效地从语义丰富的框架和提议中聚合上下文信息,从而提高性能。在ImageNet VID数据集上的实验结果表明,本文提出的GSFA在ResNet-101和ResNeXt-101下分别达到了84.8%和85.8%的mAP性能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信