EUVIMEDEUVIMED entdecken
Crossref

Deep Long-Tailed Learning: A Survey

Yifan Zhang, Bingyi Kang, Bryan Hooi, Shuicheng Yan, Jiashi Feng

IEEE Transactions on Pattern Analysis and Machine Intelligence · 01.09.2023 · 45 (9) · 10795-10816

DOI: 10.1109/tpami.2023.3268118 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, erschienen am 01.09.2023. Verfasst von Yifan Zhang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 660-mal zitiert (Crossref) und nennt 173 Literaturangaben. Gefördert von: NUS ODPRT.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep long-tailed learning, one of the most challenging problems in visual recognition, aims to train well-performing deep models from a large number of images that follow a long-tailed class distribution. In the last decade, deep learning has emerged as a powerful recognition model for learning high-quality image representations and has led to remarkable breakthroughs in generic visual recognition. However, long-tailed class imbalance, a common problem in practical visual recognition tasks, often limits the practicality of deep network based recognition models in real-world applications, since they can be easily biased towards dominant classes and perform poorly on tail classes. To address this problem, a large number of studies have been conducted in recent years, making promising progress in the field of deep long-tailed learning. Considering the rapid evolution of this field, this article aims to provide a comprehensive survey on recent advances in deep long-tailed learning. To be specific, we group existing deep long-tailed learning studies into three main categories (i.e., class re-balancing, information augmentation and module improvement), and review these methods following this taxonomy in detail. Afterward, we empirically analyze several state-of-the-art methods by evaluating to what extent they address the issue of class imbalance via a newly proposed evaluation metric, i.e., relative accuracy. We conclude the survey by highlighting important applications of deep long-tailed learning and identifying several promising directions for future research.

Förderung

  • NUS ODPRT

Zitieren

APA

Zhang, Y., Kang, B., Hooi, B., Yan, S., & Feng, J. (2023). Deep Long-Tailed Learning: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(9), 10795-10816. https://doi.org/10.1109/tpami.2023.3268118

Vancouver

Zhang Y, Kang B, Hooi B, Yan S, Feng J. Deep Long-Tailed Learning: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2023;45(9):10795-10816. doi:10.1109/tpami.2023.3268118

BibTeX
@article{Zhang2023,
  author = {Zhang, Yifan and Kang, Bingyi and Hooi, Bryan and Yan, Shuicheng and Feng, Jiashi},
  title = {Deep Long-Tailed Learning: A Survey},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2023},
  volume = {45},
  number = {9},
  pages = {10795--10816},
  doi = {10.1109/tpami.2023.3268118}
}
Kostenlos starten →