EUVIMEDEUVIMED entdecken
Crossref

Class-Incremental Learning: A Survey

Da-Wei Zhou, Qi-Wei Wang, Zhi-Hong Qi, Han-Jia Ye, De-Chuan Zhan, Ziwei Liu

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-12 · 46 (12) · 9851-9873

DOI: 10.1109/tpami.2024.3429383 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-12. Verfasst von Da-Wei Zhou und 5 weiteren Autor:innen. Die Arbeit wurde bisher 343-mal zitiert (Crossref) und nennt 222 Literaturangaben. Gefördert von: National Science and Technology, Fundamental Research Funds for the Central Universities, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep models, e.g., CNNs and Vision Transformers, have achieved impressive achievements in many vision tasks in the closed world. However, novel classes emerge from time to time in our ever-changing world, requiring a learning system to acquire new knowledge continually. Class-Incremental Learning (CIL) enables the learner to incorporate the knowledge of new classes incrementally and build a universal classifier among all seen classes. Correspondingly, when directly training the model with new class instances, a fatal problem occurs - the model tends to catastrophically forget the characteristics of former ones, and its performance drastically degrades. There have been numerous efforts to tackle catastrophic forgetting in the machine learning community. In this paper, we survey comprehensively recent advances in class-incremental learning and summarize these methods from several aspects. We also provide a rigorous and unified evaluation of 17 methods in benchmark image classification tasks to find out the characteristics of different algorithms empirically. Furthermore, we notice that the current comparison protocol ignores the influence of memory budget in model storage, which may result in unfair comparison and biased results. Hence, we advocate fair comparison by aligning the memory budget in evaluation, as well as several memory-agnostic performance measures.

Förderung

  • National Science and Technology
  • Fundamental Research Funds for the Central Universities
  • National Natural Science Foundation of China

Zitieren

APA

Zhou, D. W., Wang, Q. W., Qi, Z. H., Ye, H. J., Zhan, D. C., & Liu, Z. (2024). Class-Incremental Learning: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12), 9851-9873. https://doi.org/10.1109/tpami.2024.3429383

Vancouver

Zhou DW, Wang QW, Qi ZH, Ye HJ, Zhan DC, Liu Z. Class-Incremental Learning: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(12):9851-9873. doi:10.1109/tpami.2024.3429383

BibTeX
@article{Zhou2024,
  author = {Zhou, Da-Wei and Wang, Qi-Wei and Qi, Zhi-Hong and Ye, Han-Jia and Zhan, De-Chuan and Liu, Ziwei},
  title = {Class-Incremental Learning: A Survey},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2024},
  volume = {46},
  number = {12},
  pages = {9851--9873},
  doi = {10.1109/tpami.2024.3429383}
}
Kostenlos starten →