IDEAS home Printed from https://ideas.repec.org/a/plo/pone00/0274767.html
   My bibliography  Save this article

Saliency guided data augmentation strategy for maximally utilizing an object’s visual information

Author

Listed:
  • Junhyeok An
  • Soojin Jang
  • Junehyoung Kwon
  • Kyohoon Jin
  • YoungBin Kim

Abstract

Among the various types of data augmentation strategies, the mixup-based approach has been particularly studied. However, in existing mixup-based approaches, object loss and label mismatching can occur if random patches are utilized when constructing augmented images, and additionally, patches that do not contain objects might be included, which degrades performance. In this paper, we propose a novel augmentation method that mixes patches in a non-overlapping manner after they are extracted from the salient regions in an image. The suggested method can make effective use of object characteristics, because the constructed image consists only of visually important regions and is robust to noise. Since the patches do not occlude each other, the semantically meaningful information in the salient regions can be fully utilized. Additionally, our method is more robust to adversarial attack than the conventional augmentation method. In the experimental results, when Wide ResNet was trained on the public datasets, CIFAR-10, CIFAR-100 and STL-10, the top-1 accuracy was 97.26%, 83.99% and 82.40% respectively, which surpasses other augmentation methods.

Suggested Citation

  • Junhyeok An & Soojin Jang & Junehyoung Kwon & Kyohoon Jin & YoungBin Kim, 2022. "Saliency guided data augmentation strategy for maximally utilizing an object’s visual information," PLOS ONE, Public Library of Science, vol. 17(10), pages 1-11, October.
  • Handle: RePEc:plo:pone00:0274767
    DOI: 10.1371/journal.pone.0274767
    as

    Download full text from publisher

    File URL: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0274767
    Download Restriction: no

    File URL: https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0274767&type=printable
    Download Restriction: no

    File URL: https://libkey.io/10.1371/journal.pone.0274767?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    References listed on IDEAS

    as
    1. Yuan Zhou & Fang Dong & Yufei Liu & Zhaofu Li & JunFei Du & Li Zhang, 2020. "Forecasting emerging technologies using data augmentation and deep learning," Scientometrics, Springer;Akadémiai Kiadó, vol. 123(1), pages 1-29, April.
    2. Wei Jiang & Kai Zhang & Nan Wang & Miao Yu, 2020. "MeshCut data augmentation for deep learning in computer vision," PLOS ONE, Public Library of Science, vol. 15(12), pages 1-12, December.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Dejing Kong & Jianzhong Yang & Lingfeng Li, 2020. "Early identification of technological convergence in numerical control machine tool: a deep learning approach," Scientometrics, Springer;Akadémiai Kiadó, vol. 125(3), pages 1983-2009, December.
    2. Bowen Song & Chunjuan Luan & Danni Liang, 2023. "Identification of emerging technology topics (ETTs) using BERT-based model and sematic analysis: a perspective of multiple-field characteristics of patented inventions (MFCOPIs)," Scientometrics, Springer;Akadémiai Kiadó, vol. 128(11), pages 5883-5904, November.
    3. Zamani, Mehdi & Yalcin, Haydar & Naeini, Ali Bonyadi & Zeba, Gordana & Daim, Tugrul U, 2022. "Developing metrics for emerging technologies: identification and assessment," Technological Forecasting and Social Change, Elsevier, vol. 176(C).
    4. June Young Lee & Sejung Ahn & Dohyun Kim, 2021. "Deep learning-based prediction of future growth potential of technologies," PLOS ONE, Public Library of Science, vol. 16(6), pages 1-16, June.
    5. Yunlei Lin & Yuan Zhou, 2023. "Identification of Hydrogen-Energy-Related Emerging Technologies Based on Text Mining," Sustainability, MDPI, vol. 16(1), pages 1-19, December.
    6. Myoungjae Choi & Ohjin Kwon & Dongkyu Won & Wooseok Jang, 2021. "Identifying the Policy Direction of National R&D Programs Based on Data Envelopment Analysis and Diversity Index Approach," Sustainability, MDPI, vol. 13(22), pages 1-17, November.
    7. Guannan Xu & Weijie Hu & Yuanyuan Qiao & Yuan Zhou, 2020. "Mapping an innovation ecosystem using network clustering and community identification: a multi-layered framework," Scientometrics, Springer;Akadémiai Kiadó, vol. 124(3), pages 2057-2081, September.
    8. Yuan Zhou & Fang Dong & Yufei Liu & Liang Ran, 2021. "A deep learning framework to early identify emerging technologies in large-scale outlier patents: an empirical study of CNC machine tool," Scientometrics, Springer;Akadémiai Kiadó, vol. 126(2), pages 969-994, February.
    9. Alvaro Figueira & Bruno Vaz, 2022. "Survey on Synthetic Data Generation, Evaluation Methods and GANs," Mathematics, MDPI, vol. 10(15), pages 1-41, August.
    10. Ryosuke L. Ohniwa & Kunio Takeyasu & Aiko Hibino, 2022. "Researcher dynamics in the generation of emerging topics in life sciences and medicine," Scientometrics, Springer;Akadémiai Kiadó, vol. 127(2), pages 871-884, February.
    11. Li Yao & He Ni, 2023. "Prediction of patent grant and interpreting the key determinants: an application of interpretable machine learning approach," Scientometrics, Springer;Akadémiai Kiadó, vol. 128(9), pages 4933-4969, September.
    12. Liang Chen & Shuo Xu & Lijun Zhu & Jing Zhang & Xiaoping Lei & Guancan Yang, 2020. "A deep learning based method for extracting semantic information from patent documents," Scientometrics, Springer;Akadémiai Kiadó, vol. 125(1), pages 289-312, October.
    13. Puccetti, Giovanni & Giordano, Vito & Spada, Irene & Chiarello, Filippo & Fantoni, Gualtiero, 2023. "Technology identification from patent texts: A novel named entity recognition method," Technological Forecasting and Social Change, Elsevier, vol. 186(PB).
    14. Gozuacik, Necip & Sakar, C. Okan & Ozcan, Sercan, 2023. "Technological forecasting based on estimation of word embedding matrix using LSTM networks," Technological Forecasting and Social Change, Elsevier, vol. 191(C).
    15. Huailan Liu & Zhiwang Chen & Jie Tang & Yuan Zhou & Sheng Liu, 2020. "Mapping the technology evolution path: a novel model for dynamic topic detection and tracking," Scientometrics, Springer;Akadémiai Kiadó, vol. 125(3), pages 2043-2090, December.
    16. Hain, Daniel S. & Jurowetzki, Roman & Buchmann, Tobias & Wolf, Patrick, 2022. "A text-embedding-based approach to measuring patent-to-patent technological similarity," Technological Forecasting and Social Change, Elsevier, vol. 177(C).
    17. Zhai, Dongsheng & Zhai, Liang & Li, Mengyang & He, Xijun & Xu, Shuo & Wang, Feifei, 2022. "Patent representation learning with a novel design of patent ontology: Case study on PEM patents," Technological Forecasting and Social Change, Elsevier, vol. 183(C).
    18. Zhenyu Yang & Wenyu Zhang & Zhimin Wang & Xiaoling Huang, 2024. "A deep learning-based method for predicting the emerging degree of research topics using emerging index," Scientometrics, Springer;Akadémiai Kiadó, vol. 129(7), pages 4021-4042, July.
    19. Lijie Feng & Kehui Liu & Jinfeng Wang & Kuo-Yi Lin & Ke Zhang & Luyao Zhang, 2022. "Identifying Promising Technologies of Electric Vehicles from the Perspective of Market and Technical Attributes," Energies, MDPI, vol. 15(20), pages 1-22, October.
    20. Bekamiri, Hamid & Hain, Daniel S. & Jurowetzki, Roman, 2024. "PatentSBERTa: A deep NLP based hybrid model for patent distance and classification using augmented SBERT," Technological Forecasting and Social Change, Elsevier, vol. 206(C).

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:plo:pone00:0274767. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: plosone (email available below). General contact details of provider: https://journals.plos.org/plosone/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.