Improved Few-Shot Visual Classification

@article{Bateni2020ImprovedFV,
  title={Improved Few-Shot Visual Classification},
  author={Peyman Bateni and R. Goyal and Vaden Masrani and Frank D. Wood and L. Sigal},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2020},
  pages={14481-14490}
}
  • Peyman Bateni, R. Goyal, +2 authors L. Sigal
  • Published 2020
  • Computer Science
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Few-shot learning is a fundamental task in computer vision that carries the promise of alleviating the need for exhaustively labeled data. Most few-shot learning approaches to date have focused on progressively more complex neural feature extractors and classifier adaptation strategies, and the refinement of the task definition itself. In this paper, we explore the hypothesis that a simple class-covariance-based distance metric, namely the Mahalanobis distance, adopted into a state of the art… Expand
Learning a Universal Template for Few-shot Dataset Generalization
On the Utility of Active Instance Selection for Few-Shot Learning
Improving Few-Shot Visual Classification with Unlabelled Examples
Application of Yolo on Mask Detection Task
  • Ren Liu, Ziang Ren
  • Computer Science
  • 2021 IEEE 13th International Conference on Computer Research and Development (ICCRD)
  • 2021
Deep Metric Learning for Few-Shot Image Classification: A Selective Review
Shallow Bayesian Meta Learning for Real-World Few-Shot Recognition
...
1
2
...

References

SHOWING 1-10 OF 54 REFERENCES
Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples
Fast and Flexible Multi-Task Classification Using Conditional Neural Adaptive Processes
Deep Residual Learning for Image Recognition
[Et al].
Clustering with Bregman Divergences
Prototypical Networks for Few-shot Learning
Matching Networks for One Shot Learning
A Survey of Deep Learning-Based Object Detection
A Survey of Zero-Shot Learning
...
1
2
3
4
5
...