1 code implementation • 2 Jan 2019 • Mohammad Mahfujur Rahman, Clinton Fookes, Mahsa Baktashmotlagh, Sridha Sridharan
In the presence of large sets of labeled data, Deep Learning (DL) has accomplished extraordinary triumphs in the avenue of computer vision, particularly in object classification and recognition tasks.
no code implementations • 21 Dec 2018 • Mohammad Mahfujur Rahman, Clinton Fookes, Mahsa Baktashmotlagh, Sridha Sridharan
If DA methods are applied directly to DG by a simple exclusion of the target data from training, poor performance will result for a given task.
Ranked #115 on Domain Generalization on PACS
no code implementations • 29 Nov 2019 • Mohammad Mahfujur Rahman, Clinton Fookes, Mahsa Baktashmotlagh, Sridha Sridharan
Domain adaptation (DA) and domain generalization (DG) have emerged as a solution to the domain shift problem where the distribution of the source and target data is different.
Ranked #14 on Domain Adaptation on ImageCLEF-DA
no code implementations • 28 Apr 2021 • Mohammad Mahfujur Rahman, Clinton Fookes, Sridha Sridharan
To tackle the aforementioned problem, we introduce an end-to-end feature-norm network (FNN) which is robust to negative transfer as it does not need to match the feature distribution among the source domains.
no code implementations • 28 Apr 2021 • Mohammad Mahfujur Rahman, Clinton Fookes, Sridha Sridharan
This network can achieve source to target domain matching by capturing semantic information at the feature level and producing images for unsupervised domain adaptation from both the source and the target domains.
Generative Adversarial Network Unsupervised Domain Adaptation
no code implementations • 20 Aug 2021 • Mohammad Mahfujur Rahman, Clinton Fookes, Sridha Sridharan
Domain generalization approaches aim to learn a domain invariant prediction model for unknown target domains from multiple training source domains with different distributions.