像素就是你所需要的一切:用于显著物体检测的对抗性时空集合主动学习。

Zhenyu Wu, Wei Wang, Lin Wang, Yacong Li, Fengmao Lv, Qing Xia, Chenglizhao Chen, Aimin Hao, Shuo Li
{"title":"像素就是你所需要的一切:用于显著物体检测的对抗性时空集合主动学习。","authors":"Zhenyu Wu, Wei Wang, Lin Wang, Yacong Li, Fengmao Lv, Qing Xia, Chenglizhao Chen, Aimin Hao, Shuo Li","doi":"10.1109/TPAMI.2024.3476683","DOIUrl":null,"url":null,"abstract":"<p><p>Although weakly-supervised techniques can reduce the labeling effort, it is unclear whether a saliency model trained with weakly-supervised data (e.g., point annotation) can achieve the equivalent performance of its fully-supervised version. This paper attempts to answer this unexplored question by proving a hypothesis: there is a point-labeled dataset where saliency models trained on it can achieve equivalent performance when trained on the densely annotated dataset. To prove this conjecture, we proposed a novel yet effective adversarial spatio-temporal ensemble active learning. Our contributions are four- fold: 1) Our proposed adversarial attack triggering uncertainty can conquer the overconfidence of existing active learning methods and accurately locate these uncertain pixels. 2) Our proposed spatio-temporal ensemble strategy not only achieves outstanding performance but significantly reduces the model's computational cost. 3) Our proposed relationship-aware diversity sampling can conquer oversampling while boosting model performance. 4) We provide theoretical proof for the existence of such a point-labeled dataset. Experimental results show that our approach can find such a point-labeled dataset, where a saliency model trained on it obtained 98%-99% performance of its fully-supervised version with only ten annotated points per image. The code is available at https://github.com/wuzhenyubuaa/ASTE-AL.</p>","PeriodicalId":94034,"journal":{"name":"IEEE transactions on pattern analysis and machine intelligence","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Pixel is All You Need: Adversarial Spatio-Temporal Ensemble Active Learning for Salient Object Detection.\",\"authors\":\"Zhenyu Wu, Wei Wang, Lin Wang, Yacong Li, Fengmao Lv, Qing Xia, Chenglizhao Chen, Aimin Hao, Shuo Li\",\"doi\":\"10.1109/TPAMI.2024.3476683\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Although weakly-supervised techniques can reduce the labeling effort, it is unclear whether a saliency model trained with weakly-supervised data (e.g., point annotation) can achieve the equivalent performance of its fully-supervised version. This paper attempts to answer this unexplored question by proving a hypothesis: there is a point-labeled dataset where saliency models trained on it can achieve equivalent performance when trained on the densely annotated dataset. To prove this conjecture, we proposed a novel yet effective adversarial spatio-temporal ensemble active learning. Our contributions are four- fold: 1) Our proposed adversarial attack triggering uncertainty can conquer the overconfidence of existing active learning methods and accurately locate these uncertain pixels. 2) Our proposed spatio-temporal ensemble strategy not only achieves outstanding performance but significantly reduces the model's computational cost. 3) Our proposed relationship-aware diversity sampling can conquer oversampling while boosting model performance. 4) We provide theoretical proof for the existence of such a point-labeled dataset. Experimental results show that our approach can find such a point-labeled dataset, where a saliency model trained on it obtained 98%-99% performance of its fully-supervised version with only ten annotated points per image. The code is available at https://github.com/wuzhenyubuaa/ASTE-AL.</p>\",\"PeriodicalId\":94034,\"journal\":{\"name\":\"IEEE transactions on pattern analysis and machine intelligence\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-10-09\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE transactions on pattern analysis and machine intelligence\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/TPAMI.2024.3476683\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE transactions on pattern analysis and machine intelligence","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/TPAMI.2024.3476683","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

虽然弱监督技术可以减少标注工作量,但用弱监督数据(如点标注)训练的显著性模型是否能达到与其完全监督版本相当的性能,目前还不清楚。本文试图通过证明一个假设来回答这个尚未探索的问题:存在一个点标注数据集,在该数据集上训练的显著性模型可以达到在密集标注数据集上训练的同等性能。为了证明这一猜想,我们提出了一种新颖而有效的对抗性时空集合主动学习方法。我们的贡献包括四个方面:1)我们提出的触发不确定性的对抗性攻击可以克服现有主动学习方法的过度自信,并准确定位这些不确定像素。2) 我们提出的时空集合策略不仅实现了出色的性能,而且大大降低了模型的计算成本。3) 我们提出的关系感知多样性采样可以克服超采样,同时提高模型性能。4) 我们为这种点标记数据集的存在提供了理论证明。实验结果表明,我们的方法可以找到这样一个点标注数据集,在该数据集上训练的显著性模型在每幅图像只有十个标注点的情况下,性能达到了其完全监督版本的 98%-99%。代码见 https://github.com/wuzhenyubuaa/ASTE-AL。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Pixel is All You Need: Adversarial Spatio-Temporal Ensemble Active Learning for Salient Object Detection.

Although weakly-supervised techniques can reduce the labeling effort, it is unclear whether a saliency model trained with weakly-supervised data (e.g., point annotation) can achieve the equivalent performance of its fully-supervised version. This paper attempts to answer this unexplored question by proving a hypothesis: there is a point-labeled dataset where saliency models trained on it can achieve equivalent performance when trained on the densely annotated dataset. To prove this conjecture, we proposed a novel yet effective adversarial spatio-temporal ensemble active learning. Our contributions are four- fold: 1) Our proposed adversarial attack triggering uncertainty can conquer the overconfidence of existing active learning methods and accurately locate these uncertain pixels. 2) Our proposed spatio-temporal ensemble strategy not only achieves outstanding performance but significantly reduces the model's computational cost. 3) Our proposed relationship-aware diversity sampling can conquer oversampling while boosting model performance. 4) We provide theoretical proof for the existence of such a point-labeled dataset. Experimental results show that our approach can find such a point-labeled dataset, where a saliency model trained on it obtained 98%-99% performance of its fully-supervised version with only ten annotated points per image. The code is available at https://github.com/wuzhenyubuaa/ASTE-AL.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
EBMGC-GNF: Efficient Balanced Multi-View Graph Clustering via Good Neighbor Fusion. Integrating Neural-Symbolic Reasoning With Variational Causal Inference Network for Explanatory Visual Question Answering. Motion-Aware Dynamic Graph Neural Network for Video Compressive Sensing. Evaluation Metrics for Intelligent Generation of Graphical Game Assets: A Systematic Survey-Based Framework. Artificial Intelligence and Machine Learning Tools for Improving Early Warning Systems of Volcanic Eruptions: The Case of Stromboli.
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1