Self-Supervised Difference Detection for Weakly-Supervised Semantic Segmentation

Wataru Shimoda, Keiji Yanai
{"title":"Self-Supervised Difference Detection for Weakly-Supervised Semantic Segmentation","authors":"Wataru Shimoda, Keiji Yanai","doi":"10.1109/ICCV.2019.00531","DOIUrl":null,"url":null,"abstract":"To minimize the annotation costs associated with the training of semantic segmentation models, researchers have extensively investigated weakly-supervised segmentation approaches. In the current weakly-supervised segmentation methods, the most widely adopted approach is based on visualization. However, the visualization results are not generally equal to semantic segmentation. Therefore, to perform accurate semantic segmentation under the weakly supervised condition, it is necessary to consider the mapping functions that convert the visualization results into semantic segmentation. For such mapping functions, the conditional random field and iterative re-training using the outputs of a segmentation model are usually used. However, these methods do not always guarantee improvements in accuracy; therefore, if we apply these mapping functions iteratively multiple times, eventually the accuracy will not improve or will decrease. In this paper, to make the most of such mapping functions, we assume that the results of the mapping function include noise, and we improve the accuracy by removing noise. To achieve our aim, we propose the self-supervised difference detection module, which estimates noise from the results of the mapping functions by predicting the difference between the segmentation masks before and after the mapping. We verified the effectiveness of the proposed method by performing experiments on the PASCAL Visual Object Classes 2012 dataset, and we achieved 64.9% in the val set and 65.5% in the test set. Both of the results become new state-of-the-art under the same setting of weakly supervised semantic segmentation.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"20 1","pages":"5207-5216"},"PeriodicalIF":0.0000,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"116","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCV.2019.00531","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 116

Abstract

To minimize the annotation costs associated with the training of semantic segmentation models, researchers have extensively investigated weakly-supervised segmentation approaches. In the current weakly-supervised segmentation methods, the most widely adopted approach is based on visualization. However, the visualization results are not generally equal to semantic segmentation. Therefore, to perform accurate semantic segmentation under the weakly supervised condition, it is necessary to consider the mapping functions that convert the visualization results into semantic segmentation. For such mapping functions, the conditional random field and iterative re-training using the outputs of a segmentation model are usually used. However, these methods do not always guarantee improvements in accuracy; therefore, if we apply these mapping functions iteratively multiple times, eventually the accuracy will not improve or will decrease. In this paper, to make the most of such mapping functions, we assume that the results of the mapping function include noise, and we improve the accuracy by removing noise. To achieve our aim, we propose the self-supervised difference detection module, which estimates noise from the results of the mapping functions by predicting the difference between the segmentation masks before and after the mapping. We verified the effectiveness of the proposed method by performing experiments on the PASCAL Visual Object Classes 2012 dataset, and we achieved 64.9% in the val set and 65.5% in the test set. Both of the results become new state-of-the-art under the same setting of weakly supervised semantic segmentation.
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
弱监督语义分割的自监督差分检测
为了最大限度地减少与语义分割模型训练相关的标注成本,研究人员广泛研究了弱监督分割方法。在目前的弱监督分割方法中,采用最广泛的是基于可视化的分割方法。然而,可视化结果通常不等于语义分割。因此,为了在弱监督条件下进行准确的语义分割,需要考虑将可视化结果转化为语义分割的映射函数。对于这种映射函数,通常使用条件随机场和使用分割模型输出的迭代再训练。然而,这些方法并不总是保证准确性的提高;因此,如果我们多次迭代地应用这些映射函数,最终精度将不会提高或降低。在本文中,为了充分利用这类映射函数,我们假设映射函数的结果包含噪声,并通过去除噪声来提高精度。为了实现我们的目标,我们提出了自监督差分检测模块,该模块通过预测映射前后分割掩码之间的差异,从映射函数的结果中估计噪声。通过在PASCAL Visual Object Classes 2012数据集上的实验,验证了该方法的有效性,在val集和test集上的准确率分别达到了64.9%和65.5%。在相同的弱监督语义分割设置下,这两种结果都成为新的研究领域。
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 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Very Long Natural Scenery Image Prediction by Outpainting VTNFP: An Image-Based Virtual Try-On Network With Body and Clothing Feature Preservation Towards Latent Attribute Discovery From Triplet Similarities Gaze360: Physically Unconstrained Gaze Estimation in the Wild Attention Bridging Network for Knowledge Transfer
×
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