mouniraziz / AGLRs

Official implementation of the paper: Learn to aggregate global and local representations for few-shot learning

few-shot-classifcation few-shot-learning global image-classification image-recognition k-nearest-neighbours local meta-learning metric-learning prototypes convolutional-neural-networks one-shot-learning pytorch cub-dataset miniimagenet stanford-cars stanford-dogs-dataset tiered-imagenet

This is a PyTorch implementation of the paper: Learn to aggregate global and local representations for few-shot learning

Requirements

Pytorch 1.4.0
Torchvision 0.5.0
At least 1 GPU

Datasets

Citation

If you find our code useful for your research, please consider citing it using the bibtex:

@article{abdelaziz2023learn,
  title={Learn to aggregate global and local representations for few-shot learning},
  author={Abdelaziz, Mounir and Zhang, Zuping},
  journal={Multimedia Tools and Applications},
  pages={1--24},
  year={2023},
  publisher={Springer}
}

References

DN4
MML

About

Official implementation of the paper: Learn to aggregate global and local representations for few-shot learning

few-shot-classifcation few-shot-learning global image-classification image-recognition k-nearest-neighbours local meta-learning metric-learning prototypes convolutional-neural-networks one-shot-learning pytorch cub-dataset miniimagenet stanford-cars stanford-dogs-dataset tiered-imagenet

Languages

Language:Python 100.0%