一种基于可信度估计单元的图像分类噪声抑制深度学习策略

doi:10.3969/j.issn.0372-2112.2020.10.014

电子学报 ›› 2020, Vol. 48 ›› Issue (10): 1969-1975.DOI: 10.3969/j.issn.0372-2112.2020.10.014

一种基于可信度估计单元的图像分类噪声抑制深度学习策略

邵航¹, 黄海亮¹, 郭雨晨², 戴琼海²

1. 浙江未来技术研究院(嘉兴), 浙江嘉兴 314000;
2. 清华大学自动化系, 北京 100084

收稿日期:2019-06-10 修回日期:2020-03-22 出版日期:2020-10-25
- 作者简介:
- 邵航男,1986年9月出生,浙江江山人.2011年毕业于清华大学自动化系,获工学硕士学位.主要研究方向为人工智能与计算成像.E-mail:shaohang@tsinghua.edu.cn
  黄海亮 男,1995年6月出生,江苏如皋人.2019年毕业于杭州电子科技大学自动化学院,获硕士学位.主要研究方向为人工智能与计算成像.E-mail:huanghailiang@zfti.org
- 基金资助:
- 国家自然科学基金 (No.61827805）

Noise-Suppression Deep Learning Strategy via Reliability Estimation Gate for Image Classification

SHAO Hang¹, HUANG Hai-liang¹, GUO Yu-chen², DAI Qiong-hai²

1. Zhejiang Future Technology Institute(Jiaxing), Jiaxing, Zhejiang 314000, China;
2. Department of Automation, Tsinghua University, Beijing 100084, China

Received:2019-06-10 Revised:2020-03-22 Online:2020-10-25 Published:2020-10-25
- Supported by:
- National Natural Science Foundation of China (No.61827805)

摘要/Abstract

摘要： 近年来，深度学习越来越关注噪声抑制的研究.本文提出了一种噪声抑制深度学习策略，该策略通过构建噪声无感网络（Noise Unaware Network，NUN）和可信度估计单元（Reliability Estimation Gate，REG）来处理训练数据含有噪声的情况.通过对每个样本的可信度进行评估，调节其在训练时的权重，从而降低标签噪声对网络训练的影响.随着模型的迭代更新，标签可信数据的权重将会逐渐变大，而噪声数据的权重将会被抑制.本文通过在多个标注数据集上的实验验证了所提出的噪声抑制深度学习策略的有效性.

关键词: 深度学习, 图像分类, 噪声抑制

Abstract: In recent years, more and more attention has been paid to the study and research of noise suppression. This paper proposes a noise suppression deep learning strategy that deals with the presence of noise in training data by constructing a Noise Unaware Network (NUN) and Reliability Estimation Gate (REG). By evaluating the reliability of each sample and adjusting its weight during training, the influence of label noise on network training can be reduced. As the model is updated iteratively, the weight of clean data will gradually increase, while the weight of noise data will be suppressed. Experiments on multiple benchmark data sets demonstrate the effectiveness of the proposed deep learning strategy for noise suppression.

Key words: deep learning, image classification, noise-suppression

中图分类号:

TP301.6

邵航, 黄海亮, 郭雨晨, 等. 一种基于可信度估计单元的图像分类噪声抑制深度学习策略[J]. 电子学报, 2020, 48(10): 1969-1975.

SHAO Hang, HUANG Hai-liang, GUO Yu-chen, et al. Noise-Suppression Deep Learning Strategy via Reliability Estimation Gate for Image Classification[J]. Acta Electronica Sinica, 2020, 48(10): 1969-1975.

参考文献

[1] He K,Zhang X,Ren S,et al.Deep residual learning for image recognition[A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C].USA:IEEE,2016.770-778.
[2] Yang X,Molchanov P,Kautz J.Multilayer and multimodal fusion of deep neural networks for video classification[A].Proceedings of the 24th ACM International Conference on Multimedia[C].SA:ACM,2016.978-987.
[3] 田艳玲,张维桐,张锲石,等.图像场景分类技术综述[J].电子学报,2019,47(4):915-926. TIAN Yan-ling,ZHANG Wei-tong,ZHANG Qie-shi,et al.Review on image scene classification technology[J].Acta Electronica Sinica,2019,47(4):915-926.(in Chinese)
[4] 余游,冯林,王格格,等.一种基于伪标签的半监督少样本学习模型[J].电子学报,2019,47(11):2284-2291. YU You,FENG Lin,WANG Ge-ge,et al.A few-shot learning model based on semi-supervised with pseudo label[J].Acta Electronica Sinica,2019,47(11):2284-2291.(in Chinese)
[5] Zhu X,Wu X.Class noise vs attribute noise:A quantitative study[J].Artificial Intelligence Review,2004,22(3):177-210.
[6] Xiao T,Xia T,Yang Y,et al.Learning from massive noisy labeled data for image classification[A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C].USA:IEEE,2015.2691-2699.
[7] Frénay B,Verleysen M.Classification in the presence of label noise:a survey[J].IEEE Transactions on Neural Networks and Learning Systems,2013,25(5):845-869.
[8] Manwani N,Sastry P S.Noise tolerance under risk minimization[J].IEEE Transactions on Cybernetics,2013,43(3):1146-1151.
[9] Beigman E,Klebanov B B.Learning with annotation noise[A].Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP[C].Association for Computational Linguistics,2009.280-287.
[10] Teng C M.Evaluating noise correction[A].Pacific Rim International Conference on Artificial Intelligence[C].Berlin,Heidelberg:Springer,2000.188-198.
[11] Folleco A,Khoshgoftaar T M,Van Hulse J,et al.Software quality modeling:The impact of class noise on the random forest classifier[A].IEEE Congress on Evolutionary Computation (IEEE World Congress on Computational Intelligence)[C].USA:IEEE,2008.3853-3859.
[12] Bartlett P L,Jordan M I,McAuliffe J D.Convexity,classification,and risk bounds[J].Journal of the American Statistical Association,2006,101(473):138-156.
[13] Misra I,Lawrence Zitnick C,Mitchell M,et al.Seeing through the human reporting bias:Visual classifiers from noisy human-centric labels[A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C].USA:IEEE,2016.2930-2939.
[14] Zhu X J.Semi-supervised learning literature survey[R].University of Wisconsin-Madison Department of Computer Sciences,2005.
[15] Veit A,Alldrin N,Chechik G,et al.Learning from noisy large-scale datasets with minimal supervision[A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C].USA:IEEE,2017.839-847.
[16] Chen X,Shrivastava A,Gupta A.Neil:Extracting visual knowledge from web data[A].Proceedings of the IEEE International Conference on Computer Vision[C].USA:IEEE,2013.1409-1416.
[17] Fergus R,Weiss Y,Torralba A.Semi-supervised learning in gigantic image collections[A].Advances in Neural Information Processing Systems[C].Vancouver,BC,Canada,2009.522-530.
[18] Miranda A L B,Garcia L P F,Carvalho A C,et al.Use of classification algorithms in noise detection and elimination[A].International Conference on Hybrid Artificial Intelligence Systems[C].Berlin,Heidelberg:Springer,2009.417-424.
[19] Guan D,Yuan W,Lee Y K,et al.Identifying mislabeled training data with the aid of unlabeled data[J].Applied Intelligence,2011,35(3):345-358.
[20] Natarajan N,Dhillon I S,Ravikumar P K,et al.Learning with noisy labels[A].Advances in Neural Information Processing Systems[C].Nevada,2013.1196-1204.
[21] Sukhbaatar S,Bruna J,Paluri M,et al.Training convolutional networks with noisy labels[J].arXiv Preprint,2014,arXiv:1406.2080.
[22] Matic N,Guyon I,Bottou L,et al.Computer aided cleaning of large databases for character recognition[A].Proceedings of the 11th IAPR International Conference on Pattern Recognition (Vol.Ⅱ).Conference B:Pattern Recognition Methodology and Systems[C].USA:IEEE,1992.330-333.
[23] Wu P,Hoi S C H,Xia H,et al.Online multimodal deep similarity learning with application to image retrieval[A].Proceedings of the 21st ACM International Conference on Multimedia[C].USA:ACM,2013.153-162.
[24] Wu Z,Jiang Y G,Wang J,et al.Exploring inter-feature and inter-class relationships with deep neural networks for video classification[A].Proceedings of the 22nd ACM International Conference on Multimedia[C].USA:ACM,2014.167-176.
[25] Reed S,Lee H,Anguelov D,et al.Training deep neural networks on noisy labels with bootstrapping[J].arXiv Preprint,2014,arXiv:1412.6596.
[26] Wen Y,Zhang K,Li Z,et al.A discriminative feature learning approach for deep face recognition[A].European Conference on Computer Vision[C].Cham:Springer,2016.499-515.
[27] Schroff F,Kalenichenko D,Philbin J.Facenet:A unified embedding for face recognition and clustering[A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C].USA:IEEE,2015.815-823.
[28] Krizhevsky A,Hinton G.Learning multiple layers of features from tiny images[A].Computer Science[C].MIT,2009.1-14.
[29] LeCun Y,Bottou L,Bengio Y,et al.Gradient-based learning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
[30] Lampert C H,Nickisch H,Harmeling S.Attribute-based classification for zero-shot visual object categorization[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,36(3):453-465.
[31] Krizhevsky A,Sutskever I,Hinton G E.Imagenet classification with deep convolutional neural networks[A].Advances in Neural Information Processing Systems[C].USA,2012.1097-1105.
[32] LeCun Y,Bottou L,Bengio Y,et al.Gradient-based learning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
[33] Huang G,Liu Z,Van Der Maaten L,et al.Densely connected convolutional networks[A].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition[C].USA:IEEE,2017.4700-4708.
[34] You Q,Luo J,Jin H,et al.Building a large scale dataset for image emotion recognition:The fine print and the benchmark[A].Thirtieth AAAI Conference on Artificial Intelligence[C].USA:AAAI,2016.1-7.
[35] Machajdik J,Hanbury A.Affective image classification using features inspired by psychology and art theory[A].Proceedings of the 18th ACM International Conference on Multimedia[C].USA:ACM,2010.83-92.
[36] Rao T,Xu M,Liu H,et al.Multi-scale blocks based image emotion classification using multiple instance learning[A].IEEE International Conference on Image Processing (ICIP)[C].USA:IEEE,2016.634-638.
[37] Yang J,She D,Lai Y K,et al.Retrieving and classifying affective images via deep metric learning[A].Thirty-Second AAAI Conference on Artificial Intelligence[C].USA:AAAI,2018.1-14.

一种基于可信度估计单元的图像分类噪声抑制深度学习策略

Noise-Suppression Deep Learning Strategy via Reliability Estimation Gate for Image Classification

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	李钦, 刘伟, 牛朝阳, 宝音图, 惠周勃. 低信噪比下基于分裂EfficientNet网络的雷达信号调制方式识别[J]. 电子学报, 2023, 51(3): 675-686.
[2]	范兵兵, 何庭建, 张聪炫, 陈震, 黎明. 联合遮挡约束与残差补偿的特征金字塔光流计算方法[J]. 电子学报, 2023, 51(3): 648-657.
[3]	许新征, 李杉. 基于特征膨胀卷积模块的轻量化技术研究[J]. 电子学报, 2023, 51(2): 355-364.
[4]	王子为, 鲁继文, 周杰. 基于自适应梯度优化的二值神经网络[J]. 电子学报, 2023, 51(2): 257-266.
[5]	张聿远, 闫文君, 张立民. 基于多模态特征融合网络的空时分组码识别算法[J]. 电子学报, 2023, 51(2): 489-498.
[6]	李滔, 董秀成, 林宏伟. 基于深监督跨尺度注意力网络的深度图像超分辨率重建[J]. 电子学报, 2023, 51(1): 128-138.
[7]	郭晓轩, 冯其波, 冀振燕, 郑发家, 杨燕燕. 多线激光光条图像缺陷分割模型研究[J]. 电子学报, 2023, 51(1): 172-179.
[8]	贾童瑶, 卓力, 李嘉锋, 张菁. 基于深度学习的单幅图像去雾研究进展[J]. 电子学报, 2023, 51(1): 231-245.
[9]	何滢婕, 刘月峰, 边浩东, 郭威, 张小燕. 基于Informer的电池荷电状态估算及其稀疏优化方法[J]. 电子学报, 2023, 51(1): 50-56.
[10]	张永梅, 孙捷. 基于动静态特征双输入神经网络的咳嗽声诊断COVID-19算法[J]. 电子学报, 2023, 51(1): 202-212.
[11]	王娜, 王俊平, 朱俊辉. 基于矩阵偏序关系的形态学算子[J]. 电子学报, 2023, 51(1): 213-221.
[12]	袁海英, 成君鹏, 曾智勇, 武延瑞. Mobile_BLNet：基于Big-Little Net的轻量级卷积神经网络优化设计[J]. 电子学报, 2023, 51(1): 180-191.
[13]	王神龙, 雍宇, 吴晨睿. 基于伪孪生神经网络的低纹理工业零件6D位姿估计[J]. 电子学报, 2023, 51(1): 192-201.
[14]	吴靖, 叶晓晶, 黄峰, 陈丽琼, 王志锋, 刘文犀. 基于深度学习的单帧图像超分辨率重建综述[J]. 电子学报, 2022, 50(9): 2265-2294.
[15]	李雪莹, 王田路, 梁鹏, 王翀. 基于系统模型的用户评论中非功能需求的自动分类[J]. 电子学报, 2022, 50(9): 2079-2089.