EUVIMEDEUVIMED entdecken
Crossref

LibFewShot: A Comprehensive Library for Few-Shot Learning

Wenbin Li, Ziyi Wang, Xuesong Yang, Chuanqi Dong, Pinzhuo Tian, Tiexin Qin, Jing Huo, Yinghuan Shi, Lei Wang, Yang Gao, Jiebo Luo

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2023-12 · 45 (12) · 14938-14955

DOI: 10.1109/tpami.2023.3312125 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023-12. Verfasst von Wenbin Li und 10 weiteren Autor:innen. Die Arbeit wurde bisher 76-mal zitiert (Crossref) und nennt 70 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Jiangsu Province, Collaborative Innovation Center of Novel Software Technology and Industrialization.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Few-shot learning, especially few-shot image classification, has received increasing attention and witnessed significant advances in recent years. Some recent studies implicitly show that many generic techniques or "tricks", such as data augmentation, pre-training, knowledge distillation, and self-supervision, may greatly boost the performance of a few-shot learning method. Moreover, different works may employ different software platforms, backbone architectures and input image sizes, making fair comparisons difficult and practitioners struggle with reproducibility. To address these situations, we propose a comprehensive library for few-shot learning (LibFewShot) by re-implementing eighteen state-of-the-art few-shot learning methods in a unified framework with the same single codebase in PyTorch. Furthermore, based on LibFewShot, we provide comprehensive evaluations on multiple benchmarks with various backbone architectures to evaluate common pitfalls and effects of different training tricks. In addition, with respect to the recent doubts on the necessity of meta- or episodic-training mechanism, our evaluation results confirm that such a mechanism is still necessary especially when combined with pre-training. We hope our work can not only lower the barriers for beginners to enter the area of few-shot learning but also elucidate the effects of nontrivial tricks to facilitate intrinsic research on few-shot learning.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Jiangsu Province
  • Collaborative Innovation Center of Novel Software Technology and Industrialization
  • Jiangsu Provincial Double-Innovation Doctor Program

Zitieren

APA

Li, W., Wang, Z., Yang, X., Dong, C., Tian, P., Qin, T., Huo, J., Shi, Y., Wang, L., Gao, Y., & Luo, J. (2023). LibFewShot: A Comprehensive Library for Few-Shot Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(12), 14938-14955. https://doi.org/10.1109/tpami.2023.3312125

Vancouver

Li W, Wang Z, Yang X, Dong C, Tian P, Qin T, et al. LibFewShot: A Comprehensive Library for Few-Shot Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2023;45(12):14938-14955. doi:10.1109/tpami.2023.3312125

BibTeX
@article{Li2023,
  author = {Li, Wenbin and Wang, Ziyi and Yang, Xuesong and Dong, Chuanqi and Tian, Pinzhuo and Qin, Tiexin and Huo, Jing and Shi, Yinghuan and Wang, Lei and Gao, Yang and Luo, Jiebo},
  title = {LibFewShot: A Comprehensive Library for Few-Shot Learning},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2023},
  volume = {45},
  number = {12},
  pages = {14938--14955},
  doi = {10.1109/tpami.2023.3312125}
}
Kostenlos starten →