Skip to content

Yuxin-CV/DTN

master
Switch branches/tags

Name already in use

A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?
Code

Latest commit

 

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Diversity Transfer Network for Few-Shot Learning

Pytorch implementation for "Diversity Transfer Network for Few-Shot Learning" (deep backbone, on miniImageNet).

We also provide our trainded models.

Citations

If you find DTN useful in your research, please consider citing:

@inproceedings{chen2020diversity,
  title={Diversity Transfer Network for Few-Shot Learning.},
  author={Chen, Mengting and Fang, Yuxin and Wang, Xinggang and Luo, Heng and Geng, Yifeng and Zhang, Xinyu and Huang, Chang and Liu, Wenyu and Wang, Bo},
  booktitle={AAAI},
  pages={10559--10566},
  year={2020}
}

Introduction

Few-shot learning is a challenging task that aims at training a classifier for unseen classes with only a few training examples. The main difficulty of few-shot learning lies in the lack of intra-class diversity within insufficient training samples.

To alleviate this problem, we propose a novel generative framework, Diversity Transfer Network (DTN), that learns to transfer latent diversities from known categories and composite them with support features to generate diverse samples for novel categories in feature space. The learning problem of the sample generation (i.e., diversity transfer) is solved via minimizing an effective meta-classification loss in a single-stage network, instead of the generative loss in previous works.

Besides, an organized auxiliary task co-training(OAT) over known categories is proposed to stabilize the meta-training process of DTN.

alt text

Dataset Preprocessing & Evaluate our trained model on miniImageNet

Download the dataset from this link, put the images folder in ./miniImageNet/.

Run:

bash make.sh

We provide our trainded models for practitioners to reproduce our results listed in Table 3 of the DTN paper. alt text

Train your DTN on miniImageNet

python main_DTN.py --checkpoint 'your_checkpoint'

Evaluate your DTN on miniImageNet

# 5-way 5-shot
python main_DTN.py --N-way 5 --N-shot 5 --evaluate 1 --resume 'your_checkpoint/checkpoint.pth.tar'
# 5-way 1-shot
python main_DTN.py --N-way 5 --N-shot 1 --evaluate 1 --resume 'your_checkpoint/checkpoint.pth.tar'

License

DTN is released under the MIT license. See LICENSE for additional details.

Acknowledgment

Horizon Robotics

Thanks to the Third Party Libs

Pytorch

About

Diversity Transfer Network for Few-Shot Learning (AAAI-20, Oral)

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published