Code for 2016 TPAMI(IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE) A Comprehensive Study on Cross-View Gait Based Human Identification with Deep CNNs
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 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}
}
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].
