no code implementations • 5 Mar 2024 • Peng Qi, Zehong Yan, Wynne Hsu, Mong Li Lee
Misinformation is a prevalent societal issue due to its potential high risks.
1 code implementation • 24 Mar 2023 • Evelyn Chee, Mong Li Lee, Wynne Hsu
Class-incremental continual learning is a core step towards developing artificial intelligence systems that can continuously adapt to changes in the environment by learning new concepts without forgetting those previously learned.
1 code implementation • NeurIPS 2021 • Sandareka Wickramanayake, Wynne Hsu, Mong Li Lee
This work proposes a framework that utilizes concept-based explanations to automatically augment the dataset with new images that can cover these under-represented regions to improve the model performance.
no code implementations • 25 Jul 2021 • Jay Nandy, Wynne Hsu, Mong Li Lee
Deep learning-based models are developed to automatically detect if a retina image is `referable' in diabetic retinopathy (DR) screening.
no code implementations • 24 Jun 2021 • Sandareka Wickramanayake, Wynne Hsu, Mong Li Lee
Despite the remarkable performance, Deep Neural Networks (DNNs) behave as black-boxes hindering user trust in Artificial Intelligence (AI) systems.
1 code implementation • NAACL 2021 • Chris Samarinas, Wynne Hsu, Mong Li Lee
Automated fact-checking on a large-scale is a challenging task that has not been studied systematically until recently.
no code implementations • 9 Feb 2021 • Jay Nandy, Sudipan Saha, Wynne Hsu, Mong Li Lee, Xiao Xiang Zhu
In this paper, we propose a novel method, called \emph{Certification through Adaptation}, that transforms an AT model into a randomized smoothing classifier during inference to provide certified robustness for $\ell_2$ norm without affecting their empirical robustness against adversarial attacks.
1 code implementation • 11 Jan 2021 • Sandareka Wickramanayake, Wynne Hsu, Mong Li Lee
Learning concepts that are consistent with human perception is important for Deep Neural Networks to win end-user trust.
1 code implementation • NeurIPS 2020 • Jay Nandy, Wynne Hsu, Mong Li Lee
Among existing uncertainty estimation approaches, Dirichlet Prior Network (DPN) distinctly models different predictive uncertainty types.
2 code implementations • 5 Apr 2020 • Jay Nandy, Wynne Hsu, Mong Li Lee
Using adversarial training to defend against multiple types of perturbation requires expensive adversarial examples from different perturbation types at each training step.
no code implementations • 14 May 2018 • Jay Nandy, Wynne Hsu, Mong Li Lee
Gaussian distributions are commonly used as a key building block in many generative models.
no code implementations • EMNLP 2017 • Lahari Poddar, Wynne Hsu, Mong Li Lee
User generated content about products and services in the form of reviews are often diverse and even contradictory.
no code implementations • 15 May 2017 • Lahari Poddar, Wynne Hsu, Mong Li Lee
User opinions expressed in the form of ratings can influence an individual's view of an item.