Skip to content
/ ZSL-ADA Public

Code accompanying the paper "A Generative Framework for Zero Shot Learning with Adversarial Domain Adaptation"

19 stars 7 forks Branches Tags Activity
Star
Notifications You must be signed in to change notification settings

vkkhare/ZSL-ADA

BranchesTags

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

16 Commits
config
config
 
 
modules
modules
 
 
.gitignore
.gitignore
 
 
Overall.png
Overall.png
 
 
README.md
README.md
 
 
dataset.py
dataset.py
 
 
registry.py
registry.py
 
 
trainADA.py
trainADA.py
 
 
train_baseZSL.py
train_baseZSL.py
 
 

Repository files navigation

ZSL-ADA

Code accompanying the paper A Generative Framework for Zero Shot Learning with Adversarial Domain Adaptation published in WACV 2020, with the following author list: Varun Khare*, Divyat Mahajan*, Homanga Bharadhwaj, Vinay K. Verma, and Piyush Rai

Instructions

Modify the file config/awa_config.yml if needed and run python trainADA.py config/awa_config.yml to start training.

Brief note about the paper

This paper present a domain adaptation based generative framework for zero shot learning. We address the problem of domain shift between the seen and unseen class distribution in Zero-Shot Learning (ZSL) and seek to minimize it by developing a generative model and training it via adversarial domain adaptation. Our approach is based on end-to-end learning of the class distributions of seen classes and unseen classes. To enable the model to learn the class distributions of unseen classes, we parameterize these class distributions in terms of the class attribute information (which is available for both seen and unseen classes). This provides a very simple way to learn the class distribution of any unseen class, given only its class attribute information, and no labeled training data. Training this model with adversarial domain adaptation provides robustness against the distribution mismatch between the data from seen and unseen classes. It also engenders a novel way for training neural net based classifiers to overcome the hubness problem in Zero-Shot learning. Through a comprehensive set of experiments, we show that our model yields superior accuracies as compared to various state-of-the-art zero shot learning models, on a variety of benchmark datasets.

   
If you have questions/comments about the code or the paper, please contact Varun Khare, Divyat Mahajan, or Homanga Bharadhwaj

If you find this repo useful, please consider citing our paper

@inproceedings{khare2020generative,
  title={A Generative Framework for Zero Shot Learning with Adversarial Domain Adaptation},
  author={Khare, Varun and Mahajan, Divyat and Bharadhwaj, Homanga and Verma, Vinay Kumar and Rai, Piyush},
  booktitle={The IEEE Winter Conference on Applications of Computer Vision},
  pages={3101--3110},
  year={2020}
}

About

Code accompanying the paper "A Generative Framework for Zero Shot Learning with Adversarial Domain Adaptation"

Topics

machine-learning computer-vision paper gan zsl wacv2020

Resources

Readme
Activity

Stars

19 stars

Watchers

7 watching

Forks

7 forks
Report repository

Releases

No releases published

Packages

No packages published

Contributors 3

  •  
  •  
  •  

Languages