IDEAS home Printed from https://ideas.repec.org/a/gam/jmathe/v11y2023i13p2996-d1187226.html
   My bibliography  Save this article

Alleviating Long-Tailed Image Classification via Dynamical Classwise Splitting

Author

Listed:
  • Ye Yuan

    (Institute of Machine Intelligence, University of Shanghai for Science and Technology, Shanghai 200093, China)

  • Jiaqi Wang

    (Institute of Machine Intelligence, University of Shanghai for Science and Technology, Shanghai 200093, China)

  • Xin Xu

    (Institute of Machine Intelligence, University of Shanghai for Science and Technology, Shanghai 200093, China)

  • Ruoshi Li

    (Institute of Machine Intelligence, University of Shanghai for Science and Technology, Shanghai 200093, China)

  • Yongtong Zhu

    (Institute of Machine Intelligence, University of Shanghai for Science and Technology, Shanghai 200093, China)

  • Lihong Wan

    (Institute of Machine Intelligence, University of Shanghai for Science and Technology, Shanghai 200093, China)

  • Qingdu Li

    (Institute of Machine Intelligence, University of Shanghai for Science and Technology, Shanghai 200093, China)

  • Na Liu

    (Institute of Machine Intelligence, University of Shanghai for Science and Technology, Shanghai 200093, China)

Abstract

With the rapid increase in data scale, real-world datasets tend to exhibit long-tailed class distributions (i.e., a few classes account for most of the data, while most classes contain only a few data points). General solutions typically exploit class rebalancing strategies involving resampling and reweighting based on the sample number for each class. In this work, we explore an orthogonal direction, category splitting, which is motivated by the empirical observation that naive splitting of majority samples could alleviate the heavy imbalance between majority and minority classes. To this end, we propose a novel classwise splitting (CWS) method built upon a dynamic cluster, where classwise prototypes are updated using a moving average technique. CWS generates intra-class pseudo labels for splitting intra-class samples based on the point-to-point distance. Moreover, a group mapping module was developed to recover the ground truth of the training samples. CWS can be plugged into any existing method as a complement. Comprehensive experiments were conducted on artificially induced long-tailed image classification datasets, such as CIFAR-10-LT, CIFAR-100-LT, and OCTMNIST. Our results show that when trained with the proposed class-balanced loss, the network is able to achieve significant performance gains on long-tailed datasets.

Suggested Citation

  • Ye Yuan & Jiaqi Wang & Xin Xu & Ruoshi Li & Yongtong Zhu & Lihong Wan & Qingdu Li & Na Liu, 2023. "Alleviating Long-Tailed Image Classification via Dynamical Classwise Splitting," Mathematics, MDPI, vol. 11(13), pages 1-12, July.
  • Handle: RePEc:gam:jmathe:v:11:y:2023:i:13:p:2996-:d:1187226
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/2227-7390/11/13/2996/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/2227-7390/11/13/2996/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Dahlan Abdullah & S. Susilo & Ansari Saleh Ahmar & R. Rusli & Rahmat Hidayat, 2022. "The application of K-means clustering for province clustering in Indonesia of the risk of the COVID-19 pandemic based on COVID-19 data," Quality & Quantity: International Journal of Methodology, Springer, vol. 56(3), pages 1283-1291, June.
    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. Saemi Shin & Won Suck Yoon & Sang-Hoon Byeon, 2022. "Trends in Occupational Infectious Diseases in South Korea and Classification of Industries According to the Risk of Biological Hazards Using K-Means Clustering," IJERPH, MDPI, vol. 19(19), pages 1-19, September.
    2. Adi Jafar & Ramli Dollah & Prabhat Mittal & Asmady Idris & Jong Eop Kim & Mohd Syariefudin Abdullah & Eko Prayitno Joko & Dayangku Norasyikin Awang Tejuddin & Nordin Sakke & Noor Syakirah Zakaria & Mo, 2023. "Readiness and Challenges of E-Learning during the COVID-19 Pandemic Era: A Space Analysis in Peninsular Malaysia," IJERPH, MDPI, vol. 20(2), pages 1-15, January.
    3. Adi Jafar & Ramli Dollah & Ramzah Dambul & Prabhat Mittal & Syahruddin Awang Ahmad & Nordin Sakke & Mohammad Tahir Mapa & Eko Prayitno Joko & Oliver Valentine Eboy & Lindah Roziani Jamru & Andika Ab. , 2022. "Virtual Learning during COVID-19: Exploring Challenges and Identifying Highly Vulnerable Groups Based on Location," IJERPH, MDPI, vol. 19(17), pages 1-16, September.

    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:gam:jmathe:v:11:y:2023:i:13:p:2996-:d:1187226. 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: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    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.